© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22574
    Prev
    Next
    INDEX
    Explanations

    I made this

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

    The neuron flags first‐person past‐tense action verbs describing what the author did.

    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
     with
    -2.31
    ,
    -2.31
     who
    -2.28
     that
    -2.22
     whose
    -2.11
     which
    -1.99
     where
    -1.93
     التي
    -1.91
     other
    -1.83
     której
    -1.81
    POSITIVE LOGITS
     maig
    1.65
    recently
    1.61
     passé
    1.52
     maxime
    1.48
     POETRY
    1.45
    特に
    1.45
    especially
    1.41
    锖
    1.41
     brancas
    1.41
     murales
    1.41
    Activations Density 0.178%

    No Known Activations