Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8669
    Prev
    Next
    INDEX
    Explanations

    TV series

    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
    𝖚
    -0.75
    ОО
    -0.71
    Plusieurs
    -0.70
    生姜
    -0.68
    æv
    -0.68
     devol
    -0.67
     Abdu
    -0.66
     ответственность
    -0.66
    CHAFT
    -0.66
    UI
    -0.65
    POSITIVE LOGITS
     digitale
    0.81
     цифро
    0.78
     digitales
    0.73
    miso
    0.73
    hli
    0.71
    webView
    0.70
    Whiskey
    0.70
     digital
    0.69
     Yuc
    0.69
    bier
    0.68
    Activations Density 0.014%

    No Known Activations