© 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. 197103
    Prev
    Next
    INDEX
    Explanations

    foreign language or specific concepts

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

    named objects or entities

    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
    d
    0.52
    ing
    0.50
    ネート
    0.47
    তনাম
    0.45
    Unicode
    0.45
    TYPE
    0.44
     Κ
    0.44
    ='.
    0.44
    el
    0.44
    erci
    0.43
    POSITIVE LOGITS
     região
    0.50
     خام
    0.47
     роско
    0.46
     cinquième
    0.46
     deuxième
    0.45
     मास्टर
    0.44
     മേഖ
    0.44
     жи
    0.44
     réserve
    0.44
    κτή
    0.44
    Activations Density 0.000%

    No Known Activations