© 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. 23991
    Prev
    Next
    INDEX
    Explanations

    if, fear, Nov, look

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

    descriptions of differences and outcomes

    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
     the
    0.43
     Sensing
    0.42
     disagree
    0.41
    Restore
    0.40
     crosstalk
    0.40
    개
    0.40
    рек
    0.39
     Pupp
    0.39
     infus
    0.39
     furnish
    0.39
    POSITIVE LOGITS
    ů
    0.52
    gebaut
    0.49
    šem
    0.47
    trs
    0.45
     অসম
    0.45
    uları
    0.44
    łej
    0.43
    enses
    0.43
    owskiego
    0.43
    ử
    0.42
    Activations Density 0.000%

    No Known Activations