© 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. 147956
    Prev
    Next
    INDEX
    Explanations

    order structure method privileges

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

    menu buttons

    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
    Ons
    0.55
    _
    0.55
    7
    0.50
    DG
    0.49
    SR
    0.46
    Rewards
    0.46
    活用
    0.45
    AGE
    0.45
    8
    0.45
    Substituting
    0.45
    POSITIVE LOGITS
    inheritdoc
    0.47
    .");
    0.47
    तेश
    0.46
    ியுடன்
    0.45
     ActiveX
    0.45
    ൊ
    0.45
    ியின்
    0.44
     ماں
    0.44
    alet
    0.44
    alink
    0.44
    Activations Density 0.000%

    No Known Activations