© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135725
    Prev
    Next
    INDEX
    Explanations

    personal tracking store

    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
     Prosecutor
    0.49
     PublicKey
    0.49
     न्यायालया
    0.46
    PURE
    0.46
     ColumnName
    0.46
    र्थिक
    0.45
    ?</
    0.45
     *}\
    0.45
    ПР
    0.45
     monomials
    0.45
    POSITIVE LOGITS
    ی
    0.45
    adapted
    0.43
     personal
    0.42
    store
    0.42
    tracking
    0.41
     infrequent
    0.41
    cont
    0.41
     tram
    0.40
    Personal
    0.40
    remainder
    0.39
    Activations Density 0.006%

    No Known Activations