© 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. 76306
    Prev
    Next
    INDEX
    Explanations

    entomology, butterflies, insects

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

    trust, hate, headers, Empirical

    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
    льных
    0.48
    -
    0.46
     cope
    0.45
    cession
    0.44
    analy
    0.44
    -”
    0.44
    othermic
    0.44
     cop
    0.43
    ных
    0.43
    -"
    0.42
    POSITIVE LOGITS
     Entomology
    0.52
     Butterflies
    0.50
     इंटे
    0.49
     Vegetarian
    0.48
     Empirical
    0.48
     Imagine
    0.46
     Ethnicity
    0.46
     Graduates
    0.45
     Transcription
    0.45
     Individ
    0.44
    Activations Density 0.000%

    No Known Activations