© 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. 5694
    Prev
    Next
    INDEX
    Explanations

    minimum followed by a quantity or term

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

    minimum requirement or quantity

    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
     KIM
    0.45
    Gilbert
    0.44
    ま
    0.44
     મુ
    0.43
     jButton
    0.43
    ":"
    0.42
     Gilbert
    0.42
    胫
    0.42
     ':'
    0.42
     krát
    0.41
    POSITIVE LOGITS
     minimum
    1.55
    minimum
    1.54
     Minimum
    1.47
    Minimum
    1.39
     mínimo
    1.32
     최소
    1.31
     minimo
    1.27
     न्यूनतम
    1.23
     минимум
    1.23
    最低
    1.15
    Activations Density 0.088%

    No Known Activations