© 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. 11932
    Prev
    Next
    INDEX
    Explanations

    similar conclusions, words ending -izer, pressing

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

    initial states and beginnings

    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
     మొత్త
    0.45
    娯
    0.45
     მშ
    0.44
     lucro
    0.43
    昴
    0.43
     lihtsalt
    0.42
     immobilier
    0.42
     meest
    0.42
     reeks
    0.42
     Realty
    0.41
    POSITIVE LOGITS
     imperfect
    0.46
    ỳ
    0.46
    有两种
    0.44
    нача
    0.41
     पहला
    0.41
     প্রথমে
    0.41
    bedaan
    0.40
     shorth
    0.39
     differs
    0.39
    ̆
    0.39
    Activations Density 0.000%

    No Known Activations