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. 110107
    Prev
    Next
    INDEX
    Explanations

    requests

    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
    Off
    -0.82
     Off
    -0.69
     Behind
    -0.68
    behind
    -0.68
    Behind
    -0.68
     prefrontal
    -0.66
     coul
    -0.65
    背后的
    -0.63
     Supporting
    -0.63
    くり
    -0.63
    POSITIVE LOGITS
     Mexicana
    0.80
    Shea
    0.73
    maksi
    0.69
    混ぜ
    0.69
     тера
    0.68
    Donna
    0.67
    ZET
    0.65
    Shine
    0.65
    Ши
    0.65
     Mao
    0.65
    Activations Density 0.058%

    No Known Activations