© 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. 110502
    Prev
    Next
    INDEX
    Explanations

    diet self-control and tracking loss

    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
    パスタ
    -0.96
    holdt
    -0.83
     Hentet
    -0.83
    UNTIME
    -0.81
     Montag
    -0.79
     overdose
    -0.78
     recomendamos
    -0.78
     године
    -0.78
    warming
    -0.77
    женной
    -0.77
    POSITIVE LOGITS
     accountability
    1.30
     cravings
    1.24
     temptations
    1.21
     temptation
    1.03
     sabo
    1.02
     Temptation
    1.01
     cheat
    1.01
     logging
    1.00
     Cheat
    0.99
     Erfol
    0.97
    Activations Density 0.030%

    No Known Activations