© 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. 186520
    Prev
    Next
    INDEX
    Explanations

    finding kind or subsidiaries

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

    phrasing actions or conditions

    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
    ITZ
    0.47
    م
    0.45
    تر
    0.44
    ترل
    0.44
    Ontario
    0.44
     $('
    0.43
    고요
    0.43
     ouvertes
    0.43
    Fl
    0.43
     -->'
    0.43
    POSITIVE LOGITS
     வரலாற்று
    0.54
    ប្ប
    0.46
    ından
    0.46
     Initially
    0.46
    riften
    0.46
     ভূত
    0.46
    ləşdir
    0.46
     મુજબ
    0.46
     Drafting
    0.46
     வைத்துக்
    0.46
    Activations Density 0.001%

    No Known Activations