© 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. 182244
    Prev
    Next
    INDEX
    Explanations

    result or full money

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

    revealing information or 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
    ا
    0.55
    ’
    0.55
    ba
    0.52
     Baked
    0.51
     sebagai
    0.50
     Tesco
    0.48
    ંગી
    0.47
     október
    0.46
     untuk
    0.46
     ia
    0.46
    POSITIVE LOGITS
    زيد
    0.46
    👮
    0.45
    nameSort
    0.44
    зя
    0.44
    splitContainer
    0.43
    に関して
    0.42
     localidad
    0.42
    training
    0.42
     propriety
    0.41
    휀
    0.41
    Activations Density 0.000%

    No Known Activations