© 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. 14859
    Prev
    Next
    INDEX
    Explanations

    build my church; days; rock of; ring up Circus; to me

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

    sigmoid derivative calculation

    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
    ﻦ
    0.52
    ну
    0.49
    vil
    0.42
    ویر
    0.42
    臥
    0.41
    خير
    0.41
    仼
    0.41
     MyDB
    0.41
    క్కి
    0.41
    في
    0.41
    POSITIVE LOGITS
     bygg
    0.49
     grootste
    0.49
     buiten
    0.49
     ado
    0.46
     predictors
    0.46
     secession
    0.45
     gimm
    0.45
    鳃
    0.45
     jähr
    0.45
     godina
    0.44
    Activations Density 0.000%

    No Known Activations