© 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. 3315
    Prev
    Next
    INDEX
    Explanations

    grow up, water sputter, function of

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

    harmful characteristics

    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
    ur
    0.53
    ät
    0.53
    稃
    0.52
     समाजवादी
    0.52
    immun
    0.50
     নির্ধারিত
    0.50
    tes
    0.49
     Immunology
    0.49
     Mexique
    0.48
     پرومو
    0.48
    POSITIVE LOGITS
     Gallagher
    0.49
    াবহ
    0.48
     acetate
    0.47
     objects
    0.46
    ბ
    0.46
     comer
    0.45
    エイ
    0.45
     noble
    0.44
    ാലി
    0.44
     curios
    0.44
    Activations Density 0.000%

    No Known Activations