© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22382
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    quantifiers or determiners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dźwię
    0.50
     dentées
    0.46
     filede
    0.45
    🕍
    0.45
     przyję
    0.45
    Пор
    0.45
    .~
    0.43
     natura
    0.43
     Avrupa
    0.43
     verildi
    0.43
    POSITIVE LOGITS
     com
    0.50
    in
    0.47
     أ
    0.44
    com
    0.43
    goals
    0.42
    銈
    0.42
    trick
    0.42
    ین
    0.41
    sums
    0.41
     אפ
    0.41
    Activations Density 0.000%

    No Known Activations