© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10177
    Prev
    Next
    INDEX
    Explanations

    associated therewith

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    趼
    -2.56
    Ꮏ
    -2.39
    ࿚
    -2.16
    鶿
    -2.14
    .".
    -2.11
    鲀
    -2.11
    .'"
    -2.06
    anleitung
    -2.06
    ῞
    -2.03
     něm
    -2.02
    POSITIVE LOGITS
    咴
    3.03
    的
    2.67
     There
    2.53
    埽
    2.50
     When
    2.50
    the
    2.47
    塒
    2.27
    寕
    2.23
     Like
    2.23
    筇
    2.22
    Activations Density 0.000%

    No Known Activations