© 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. 119028
    Prev
    Next
    INDEX
    Explanations

    Country Matters, Ally Bank, News broadcasting

    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
     luxo
    -0.77
    IMIN
    -0.72
    хождения
    -0.71
    ppens
    -0.68
     TÜ
    -0.68
     製品
    -0.66
    Hic
    -0.66
     Adieu
    -0.64
     Visita
    -0.63
    <0xA7>
    -0.63
    POSITIVE LOGITS
     wichtig
    0.90
    Agents
    0.74
    ஞ
    0.71
    ridis
    0.71
     меда
    0.70
    创建
    0.70
     algebra
    0.69
    SerialPort
    0.69
    cial
    0.68
    âte
    0.68
    Activations Density 0.047%

    No Known Activations