© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110599
    Prev
    Next
    INDEX
    Explanations

    nationally, conventionally, emotionally

    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
     básico
    -0.79
     والك
    -0.76
     Hell
    -0.74
    дует
    -0.74
     Idle
    -0.74
     pesado
    -0.74
    yness
    -0.73
     dư
    -0.73
     fár
    -0.73
    性别
    -0.73
    POSITIVE LOGITS
    ally
    2.53
    ality
    2.02
    als
    1.98
    nal
    1.87
    ional
    1.84
    ALLY
    1.80
    al
    1.76
    alised
    1.65
    onal
    1.55
    ális
    1.52
    Activations Density 0.055%

    No Known Activations