© 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. 178774
    Prev
    Next
    INDEX
    Explanations

    specific phrases and collocations

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

    lack of

    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
    锹
    0.55
     Đế
    0.53
    лит
    0.52
    вара
    0.48
    getHost
    0.48
     svoju
    0.46
    বিস্ত
    0.45
    யர்
    0.44
     Diện
    0.44
    undaria
    0.44
    POSITIVE LOGITS
     parlare
    0.52
     eternally
    0.47
     in
    0.46
     prominent
    0.46
     topical
    0.46
    氰
    0.46
     sufficient
    0.46
     facilitated
    0.45
     تحديد
    0.45
    У
    0.45
    Activations Density 0.000%

    No Known Activations