© 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. 44614
    Prev
    Next
    INDEX
    Explanations

    subscripts with numbers or letters

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

    indices and parameters

    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
    तरी
    0.49
     Auc
    0.45
    احث
    0.45
    スマス
    0.45
    ္
    0.45
    䚰
    0.44
    ScriptBuf
    0.44
     鳥
    0.44
     hydraz
    0.44
    த்ரே
    0.43
    POSITIVE LOGITS
    1
    0.55
    3
    0.53
    ız
    0.49
    haul
    0.47
    4
    0.46
    '
    0.45
    shock
    0.45
     cũ
    0.44
     রেখে
    0.44
    ità
    0.44
    Activations Density 0.000%

    No Known Activations