© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 60215
    Prev
    Next
    INDEX
    Explanations

    insurance, championing, pedestal

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

    stacking or piling

    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
    п
    0.59
    ನ
    0.53
    м
    0.46
     microorganisms
    0.45
    た
    0.44
    н
    0.43
    ம
    0.43
    ш
    0.41
    க்
    0.41
    р
    0.41
    POSITIVE LOGITS
     আসছে
    0.52
     되면
    0.50
    ubat
    0.47
     되었
    0.47
     कैसे
    0.47
    fungen
    0.46
     aaya
    0.46
     dagen
    0.46
    দাতা
    0.46
    wna
    0.46
    Activations Density 0.000%

    No Known Activations