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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82577
    Prev
    Next
    INDEX
    Explanations

    death induced

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

    programming and technical code elements, particularly in relation to web development and software documentation.

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

    This neuron flags code‐style identifiers and keywords (e.g. constructor/class names and other programming tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    usement
    -0.75
    Rights
    -0.72
     Rights
    -0.72
    avedra
    -0.71
     Transportation
    -0.71
     Gap
    -0.71
    uco
    -0.71
     ThemeData
    -0.68
     inspection
    -0.67
     rights
    -0.65
    POSITIVE LOGITS
    下班
    0.67
    orry
    0.67
    ́ng
    0.66
     Glä
    0.66
     Linton
    0.65
    sse
    0.65
    formular
    0.64
    UrlHelper
    0.64
     Mucha
    0.63
    ריך
    0.62
    Activations Density 0.065%

    No Known Activations