© 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. 94761
    Prev
    Next
    INDEX
    Explanations

    first, total, measures, win

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

    explaining definitions or origins

    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
     mA
    0.48
    ívá
    0.46
     enregistré
    0.44
     您
    0.42
    اه
    0.41
     ਕਿਸ
    0.41
    duh
    0.41
     وسهلا
    0.40
     UTA
    0.40
     مم
    0.40
    POSITIVE LOGITS
    u
    0.54
    f
    0.44
    творю
    0.43
    бори
    0.43
    নারায়ণ
    0.42
    ্রম
    0.42
    蒡
    0.41
     Salisbury
    0.41
    isbury
    0.41
     flamb
    0.40
    Activations Density 0.000%

    No Known Activations