© 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. 946
    Prev
    Next
    INDEX
    Explanations

    perennial plants and candidates

    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
    廰
    -3.17
    筇
    -2.98
    皷
    -2.72
    怱
    -2.67
     they
    -2.55
    ING
    -2.52
    歘
    -2.45
     acusa
    -2.44
    ཽ
    -2.42
    蕷
    -2.36
    POSITIVE LOGITS
    '
    2.84
     –
    2.84
    ization
    2.77
    鸶
    2.61
    Even
    2.53
    that
    2.47
     クー
    2.36
    ⢓
    2.34
    T
    2.33
     have
    2.28
    Activations Density 0.003%

    No Known Activations