© 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. 61307
    Prev
    Next
    INDEX
    Explanations

    blue sky birds singing

    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
    ⻬
    -1.98
    跸
    -1.76
     fotografii
    -1.56
    aritions
    -1.55
    ToProps
    -1.55
    viembre
    -1.53
     Sebagai
    -1.51
     wichtigen
    -1.51
    ruecos
    -1.48
     üblichen
    -1.48
    POSITIVE LOGITS
    '
    1.72
    )
    1.71
     that
    1.67
     of
    1.53
     Italian
    1.48
    [
    1.47
    ",
    1.45
    e
    1.44
    that
    1.34
     هایی
    1.34
    Activations Density 0.008%

    No Known Activations