© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27268
    Prev
    Next
    INDEX
    Explanations

    bank transactions and accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isVideo
    0.57
     servidor
    0.56
     pesc
    0.55
     decorate
    0.54
    as
    0.52
     የ
    0.52
    JsonProperty
    0.52
     الدي
    0.52
     لك
    0.50
     已
    0.50
    POSITIVE LOGITS
    ک
    0.57
    ING
    0.56
     failings
    0.53
     operations
    0.52
    ח
    0.52
    giveness
    0.52
    ود
    0.51
     Banking
    0.50
     auditions
    0.49
     outings
    0.49
    Activations Density 0.053%

    No Known Activations