© 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. 119042
    Prev
    Next
    INDEX
    Explanations

    French names and words

    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
    vő
    -0.76
    ﺑ
    -0.75
    unjungi
    -0.74
    ffen
    -0.73
    chauffer
    -0.73
    Dum
    -0.73
    ('../
    -0.73
    が
    -0.71
    atie
    -0.71
    ī
    -0.71
    POSITIVE LOGITS
    ellingham
    0.89
    []={
    0.88
     telefonu
    0.79
     memori
    0.77
    一步
    0.76
     Appetit
    0.76
    omalies
    0.75
     recientemente
    0.75
    cluding
    0.75
     soared
    0.74
    Activations Density 0.005%

    No Known Activations