© 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. 225825
    Prev
    Next
    INDEX
    Explanations

    collocations of common words

    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
    ण्याचे
    0.54
    рной
    0.49
     आरोप
    0.49
    ളുടെ
    0.47
    अगर
    0.47
    懿
    0.45
    ର୍
    0.45
    衮
    0.45
    若是
    0.45
    SER
    0.45
    POSITIVE LOGITS
     vuttam
    0.46
    ınıza
    0.45
     khác
    0.45
     nurs
    0.44
     dedicate
    0.43
     Turbine
    0.42
     besuchte
    0.42
    unat
    0.42
     CJ
    0.42
    cenie
    0.41
    Activations Density 0.000%

    No Known Activations