© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 68005
    Prev
    Next
    INDEX
    Explanations

    Cura, IBM, Schl, reticulum, Eisen

    np_acts-logits-general · gemini-2.5-flash-lite

    names of companies, organizations, and scientific terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires most strongly on standalone proper‐name or technical Latin-style terms (e.g. “Cura,” “Curaçao,” “reticulum,” “IBM”), i.e. capitalized or specialized nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -2.73
    s
    -2.73
     techniczne
    -2.56
    摭
    -2.48
     meines
    -2.33
    沨
    -2.25
    鶿
    -2.22
    a
    -2.17
    $
    -2.17
     nasze
    -2.13
    POSITIVE LOGITS
     seeming
    2.61
     aseguró
    2.42
     esame
    2.41
     стал
    2.41
    because
    2.36
     He
    2.30
     porque
    2.22
     márm
    2.22
    
    2.20
     explicó
    2.14
    Activations Density 0.050%

    No Known Activations