© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 117835
    Prev
    Next
    INDEX
    Explanations

    hunt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     পা
    -0.88
    годні
    -0.77
     electrical
    -0.76
    ótica
    -0.71
    cdata
    -0.71
    xdb
    -0.69
     Pierce
    -0.69
     lát
    -0.69
     especias
    -0.69
     tested
    -0.68
    POSITIVE LOGITS
     hunt
    2.42
     hunting
    2.34
     hunts
    2.28
     hounds
    2.14
     fox
    2.13
     Hunt
    2.03
    hunting
    2.02
    Hunt
    1.95
     hunted
    1.85
    hunt
    1.83
    Activations Density 0.022%

    No Known Activations