© 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. 69486
    Prev
    Next
    INDEX
    Explanations

    basic version, sequels were

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

    Bank Statement

    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
     ventral
    0.45
    ovalent
    0.44
    鉚
    0.43
    unton
    0.42
    Asp
    0.41
     ಬಂದ
    0.41
     risked
    0.40
    Lng
    0.39
    OSPHER
    0.39
     Normdatei
    0.39
    POSITIVE LOGITS
     devuelve
    0.52
    ({
    0.49
     کہاں
    0.48
    を行い
    0.44
    做什么
    0.44
     что
    0.43
     apakah
    0.43
    りと
    0.43
     آیا
    0.43
    ੱਸ
    0.43
    Activations Density 0.002%

    No Known Activations