© 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. 110501
    Prev
    Next
    INDEX
    Explanations

    hyperbole or exaggeration

    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
     Stupid
    -0.85
    لیت
    -0.77
    참
    -0.77
     giggling
    -0.71
     lamen
    -0.69
    TokenNameRBRACE
    -0.68
    ímos
    -0.68
    エンド
    -0.68
     повин
    -0.68
    PONE
    -0.67
    POSITIVE LOGITS
     hyper
    4.34
    hyper
    3.95
     exaggeration
    3.81
     hyperbolic
    3.80
    Hyper
    3.69
     Hyper
    3.61
     гипер
    2.95
     exaggerate
    2.70
     hiper
    2.70
     HYPER
    2.69
    Activations Density 0.044%

    No Known Activations