© 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. 44758
    Prev
    Next
    INDEX
    Explanations

    pin stripe

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

    The neuron strongly responds to technical specification tokens—especially numbers and measurement‐unit words—in procedural or product‐description contexts.

    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
     веке
    -1.41
    vellous
    -1.33
    eniendo
    -1.32
    Ayrıca
    -1.31
     tämä
    -1.29
     amelyek
    -1.28
    Forrás
    -1.27
     Bildschirm
    -1.26
     вони
    -1.25
    Cuándo
    -1.25
    POSITIVE LOGITS
     qualsiasi
    1.25
     the
    1.22
     or
    1.19
    . 
    1.18
     whatever
    1.18
     of
    1.12
    ใด
    1.10
     any
    1.09
     begle
    1.08
     tuta
    1.05
    Activations Density 0.144%

    No Known Activations