© 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. 217607
    Prev
    Next
    INDEX
    Explanations

    "more content", "Intervention costs", "foregoing limitation"

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

    but I

    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
     inférieure
    0.50
    =',
    0.48
    ドラゴン
    0.47
    ிஸ்த
    0.47
     DBS
    0.44
    amata
    0.43
     Uygh
    0.43
     奥
    0.43
    ifiable
    0.43
     Easter
    0.43
    POSITIVE LOGITS
    with
    0.51
     với
    0.46
    dengan
    0.46
     dgn
    0.46
     señor
    0.46
     с
    0.45
     עם
    0.44
     Avec
    0.44
     ريا
    0.44
     pued
    0.43
    Activations Density 0.000%

    No Known Activations