© 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. 136071
    Prev
    Next
    INDEX
    Explanations

    fishing, families, fisheries, forests

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

    flags and file words

    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
    नो
    0.46
    
    0.45
    ะนั้น
    0.43
    発送
    0.42
     والمع
    0.42
     necklaces
    0.42
    ন
    0.42
    Бо
    0.42
    อาการ
    0.41
    hältnisse
    0.41
    POSITIVE LOGITS
     f
    0.82
     Fisheries
    0.76
     F
    0.73
     Families
    0.70
     fisheries
    0.68
     family
    0.68
     Fishing
    0.68
     families
    0.66
     Forests
    0.66
     fishing
    0.64
    Activations Density 0.048%

    No Known Activations