© 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. 138270
    Prev
    Next
    INDEX
    Explanations

    simple metal, training opportunity, bank issuing

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

    intent classification

    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
     Catholics
    0.48
     फट
    0.48
    𝘧
    0.48
    getHeight
    0.47
     ஆகவே
    0.47
     αυτο
    0.47
    acje
    0.47
    றுத்த
    0.47
     জুন
    0.46
    innerHeight
    0.46
    POSITIVE LOGITS
     FEM
    0.50
    ם
    0.47
    ب
    0.44
     Composer
    0.43
    FEM
    0.42
    RIC
    0.40
     ARI
    0.40
     ANSI
    0.40
     Computation
    0.40
    :
    0.40
    Activations Density 0.000%

    No Known Activations