© 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. 245969
    Prev
    Next
    INDEX
    Explanations

    cat and dog allergens

    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
     різ
    0.50
     réalisée
    0.49
    klin
    0.49
     ممالک
    0.49
    manın
    0.48
    辗
    0.46
    ivät
    0.46
    ຖານ
    0.45
    餚
    0.45
    bedaan
    0.45
    POSITIVE LOGITS
     slow
    0.56
     FAST
    0.54
     I
    0.53
     VB
    0.53
     YAML
    0.52
     Wi
    0.52
    o
    0.50
     SAM
    0.50
     JAM
    0.50
     fabric
    0.50
    Activations Density 0.000%

    No Known Activations