© 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. 20004
    Prev
    Next
    INDEX
    Explanations

    dual core technology

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

    without sacrificing significant

    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
    は
    0.50
    ницы
    0.49
    стого
    0.46
    adilan
    0.46
    장
    0.46
    мето
    0.46
    Dv
    0.46
    при
    0.45
    Jumlah
    0.45
    δε
    0.44
    POSITIVE LOGITS
     residente
    0.49
     Kerm
    0.46
     raffin
    0.45
     amortization
    0.45
     a
    0.44
     Kurds
    0.44
    arming
    0.44
     conferring
    0.44
     posits
    0.44
     ingred
    0.43
    Activations Density 0.000%

    No Known Activations