© 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. 204811
    Prev
    Next
    INDEX
    Explanations

    like...wine

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

    requirements, methods, suggests

    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
    SE
    0.52
    Z
    0.52
     for
    0.50
    Activated
    0.49
    YES
    0.48
    Han
    0.48
    St
    0.47
    Claudia
    0.47
     activation
    0.46
    Mal
    0.46
    POSITIVE LOGITS
    beelding
    0.54
    詓
    0.50
    zinho
    0.50
    riamo
    0.49
    тою
    0.48
    сия
    0.48
     ہوتے
    0.47
    ukunft
    0.47
     آتے
    0.47
    きます
    0.46
    Activations Density 0.000%

    No Known Activations