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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 635
    Prev
    Next
    INDEX
    Explanations

    I like to express myself

    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
     on
    -2.19
     with
    -2.08
     both
    -1.93
     all
    -1.84
     but
    -1.69
     or
    -1.69
     and
    -1.62
     seemingly
    -1.60
    如何
    -1.56
     using
    -1.54
    POSITIVE LOGITS
     Inſ
    1.75
     confron
    1.72
    provides
    1.69
     Eſ
    1.64
    畱
    1.63
     assistente
    1.62
     adesivo
    1.62
     farmaco
    1.61
     dager
    1.59
    垆
    1.57
    Activations Density 0.015%

    No Known Activations