© 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. 130998
    Prev
    Next
    INDEX
    Explanations

    author, loss, Punjab

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

    important concepts and datasets

    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
    Hide
    0.49
     Tats
    0.47
     Hide
    0.47
     Childhood
    0.47
     Faithful
    0.45
    КТ
    0.45
    p
    0.45
    HID
    0.44
    H
    0.44
    KAK
    0.44
    POSITIVE LOGITS
    ться
    0.57
    getSaveLocation
    0.56
     الدين
    0.48
    ময়
    0.47
    тыми
    0.47
     descenso
    0.46
     turismo
    0.46
     contenuto
    0.46
    adero
    0.46
    ماً
    0.46
    Activations Density 0.000%

    No Known Activations