© 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. 131860
    Prev
    Next
    INDEX
    Explanations

    env.scratchFolder, Functions::, getAttribute(, Meta tags

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

    web request data access

    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
     business
    0.48
     management
    0.44
     manip
    0.44
     process
    0.43
     spending
    0.42
     data
    0.42
    ({},
    0.41
     structured
    0.41
     stored
    0.39
     science
    0.39
    POSITIVE LOGITS
    栃木
    0.51
     шум
    0.49
     मौखिक
    0.43
     terzo
    0.43
    Apellido
    0.43
     únicos
    0.42
    Belle
    0.42
    ピンク
    0.41
    inizio
    0.41
     ܠ
    0.41
    Activations Density 0.001%

    No Known Activations