© 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. 153889
    Prev
    Next
    INDEX
    Explanations

    negotiators were, strife suffered

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

    financial data and knowledge cut-off

    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
    enciado
    0.50
     میلیون
    0.49
     cuentas
    0.48
     عدة
    0.48
    sciutto
    0.46
     bogged
    0.46
    થ
    0.46
    mato
    0.45
    ncia
    0.45
     کان
    0.45
    POSITIVE LOGITS
    ช่วง
    0.55
    ',
    0.46
    iky
    0.46
     quirky
    0.46
     DOR
    0.45
     DOP
    0.45
     किनारे
    0.45
     Lagrange
    0.45
     eder
    0.44
     裏
    0.44
    Activations Density 0.000%

    No Known Activations