© 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. 121733
    Prev
    Next
    INDEX
    Explanations

    to choose

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

    traffic and coverage practices

    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
    replaceable
    0.47
    م
    0.45
    ngrx
    0.43
    ق
    0.42
     Diseases
    0.42
    reserved
    0.42
    0.42
    akkan
    0.41
    ancest
    0.41
    nullable
    0.41
    POSITIVE LOGITS
     קי
    0.44
     тща
    0.44
     tı
    0.43
    <unused582>
    0.43
     рэгістра
    0.42
     berjalan
    0.41
     sağlay
    0.41
     decide
    0.41
     rulemaking
    0.40
     Walking
    0.40
    Activations Density 0.006%

    No Known Activations