© 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. 138277
    Prev
    Next
    INDEX
    Explanations

    explaining specific terminology

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

    extracting lists

    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
     কয়েক
    0.45
    з
    0.45
    SSL
    0.45
     worm
    0.44
    ulai
    0.44
    wireless
    0.44
     সোভিয়েত
    0.44
    NC
    0.43
     Complexes
    0.42
    无线
    0.42
    POSITIVE LOGITS
     kulture
    0.45
     Geißler
    0.45
    animity
    0.45
    系的
    0.45
    系
    0.43
     مبلغ
    0.43
    𝐧
    0.43
     خس
    0.42
    kező
    0.42
     vielfält
    0.42
    Activations Density 0.000%

    No Known Activations