© 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. 98304
    Prev
    Next
    INDEX
    Explanations

    leaders, chefs, fathers

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

    allows or enables

    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
    amoto
    0.43
     हुन
    0.42
     靴
    0.41
    margin
    0.41
    ymmetry
    0.40
    䬲
    0.40
    lá
    0.40
    angulo
    0.40
     madrid
    0.39
    l
    0.39
    POSITIVE LOGITS
     nawet
    0.56
     fathers
    0.50
     logiciel
    0.48
    бліоте
    0.47
     Fathers
    0.46
     leaders
    0.46
     volle
    0.45
     Chefs
    0.45
     Leaders
    0.44
     peuple
    0.44
    Activations Density 0.003%

    No Known Activations