© 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. 148194
    Prev
    Next
    INDEX
    Explanations

    budget, offense, framing

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

    managed by / accessed through / spending on

    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
    E
    0.47
    \
    0.44
    0.43
    G
    0.43
    D
    0.42
    <0x80>
    0.42
    fahren
    0.42
    V
    0.42
    L
    0.41
    U
    0.41
    POSITIVE LOGITS
     トップス
    0.53
     নৌকা
    0.52
     erh
    0.51
     เรือ
    0.49
     महागठबंधन
    0.49
     responden
    0.48
     cálculo
    0.48
     നടത്തിയ
    0.48
     décider
    0.48
    ється
    0.48
    Activations Density 0.000%

    No Known Activations