© 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. 110458
    Prev
    Next
    INDEX
    Explanations

    couldn't be bothered

    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
     PLWABN
    -0.79
    Spurs
    -0.73
     rũ
    -0.70
     '\\;'
    -0.70
     才
    -0.70
     almacenamiento
    -0.70
    venia
    -0.70
    눌
    -0.69
    ૧
    -0.68
    结
    -0.68
    POSITIVE LOGITS
     bothered
    2.78
     bother
    1.66
     be
    1.08
     bothering
    1.08
    CBA
    1.06
     troubled
    1.03
     ar
    1.02
     CBA
    0.98
    cba
    0.94
     effort
    0.91
    Activations Density 0.041%

    No Known Activations