© 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. 133358
    Prev
    Next
    INDEX
    Explanations

    codes given, remember that, simply assembling

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

    the word "son"

    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
     daj
    0.55
     richiesta
    0.47
    ْب
    0.47
     приз
    0.46
     fü
    0.45
    忥
    0.45
    ج
    0.45
     CET
    0.45
     obraz
    0.45
    佹
    0.45
    POSITIVE LOGITS
    umur
    0.49
     uncomplicated
    0.46
    IQ
    0.45
     በመ
    0.44
     awakens
    0.42
     که
    0.41
     purchased
    0.41
     Antilles
    0.41
     पेंगे
    0.40
     которой
    0.40
    Activations Density 0.000%

    No Known Activations