© 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. 163092
    Prev
    Next
    INDEX
    Explanations

    products and services

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

    understandably increasing genre sadness summary associate harvested

    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
     Vice
    0.49
     vice
    0.44
     الحديث
    0.43
    稅
    0.43
    已經
    0.43
     मद्देन
    0.43
    為
    0.43
     depress
    0.42
    လျ
    0.42
    ဆို
    0.42
    POSITIVE LOGITS
    dött
    0.50
    imis
    0.48
    ĝo
    0.46
     coscienza
    0.46
     maestra
    0.45
    penup
    0.44
    g
    0.43
    iest
    0.43
     Lauren
    0.43
    ”),
    0.43
    Activations Density 0.000%

    No Known Activations