© 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. 196254
    Prev
    Next
    INDEX
    Explanations

    non-english text snippets

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

    wanting or planning something

    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
    錤
    0.46
    t
    0.46
    vendor
    0.46
    VING
    0.46
    ving
    0.45
    বেশী
    0.45
    urno
    0.45
     온
    0.44
    value
    0.43
    lad
    0.43
    POSITIVE LOGITS
     monstros
    0.53
     moż
    0.46
    ཾ
    0.46
     siè
    0.44
     सड़
    0.44
    йдз
    0.44
     freehold
    0.43
    ഘോഷ
    0.43
     попада
    0.43
     způso
    0.42
    Activations Density 0.000%

    No Known Activations