© 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. 244487
    Prev
    Next
    INDEX
    Explanations

    places and intents

    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
    ס
    0.71
    羅
    0.54
    POSITORY
    0.54
    renowned
    0.52
    س
    0.52
    ભાર
    0.52
    ROUTE
    0.52
    directory
    0.50
     inteligencia
    0.50
    jdbcType
    0.50
    POSITIVE LOGITS
     Also
    0.50
     SC
    0.49
     I
    0.48
     BE
    0.48
     NHE
    0.48
     of
    0.47
     Have
    0.47
     Propri
    0.47
     Of
    0.46
     Tara
    0.46
    Activations Density 0.001%

    No Known Activations