© 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. 134316
    Prev
    Next
    INDEX
    Explanations

    requested hotel services

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

    student with; mom,; faith

    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
    лм
    0.64
     décision
    0.59
    Гц
    0.54
    ми
    0.54
    мі
    0.51
    𒈪
    0.51
    에게
    0.51
     évolution
    0.50
    Ako
    0.50
     intervento
    0.49
    POSITIVE LOGITS
     brownish
    0.52
     oli
    0.49
     khas
    0.46
     *-
    0.46
     hotel
    0.45
     ye
    0.45
     heterogeneous
    0.44
     college
    0.44
     tenis
    0.43
    ectar
    0.43
    Activations Density 0.001%

    No Known Activations