© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109809
    Prev
    Next
    INDEX
    Explanations

    free software license

    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_34/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
     Olin
    -0.82
    engeance
    -0.80
    ίνη
    -0.77
    CLUYE
    -0.76
    作為
    -0.76
    nop
    -0.75
     Thumbnails
    -0.73
    worm
    -0.70
    tell
    -0.70
    ctime
    -0.69
    POSITIVE LOGITS
    𝔰
    0.70
     dulces
    0.68
    ecap
    0.68
    varez
    0.66
     приро
    0.65
    的过程
    0.64
     drastic
    0.63
    enschaft
    0.63
    Rape
    0.63
    vski
    0.63
    Activations Density 0.032%

    No Known Activations