© 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. 110562
    Prev
    Next
    INDEX
    Explanations

    fines and penalties

    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
     نہیں
    -0.70
    orgs
    -0.69
    cilla
    -0.67
     Ishikawa
    -0.65
    Commission
    -0.65
    Gall
    -0.64
     unsafe
    -0.64
    mbang
    -0.63
    선
    -0.62
     blinks
    -0.61
    POSITIVE LOGITS
     fixed
    1.29
    Fixed
    1.18
     Fixed
    1.16
    fixed
    1.07
     FIXED
    1.01
    FIXED
    0.97
     penalty
    0.94
     Penalty
    0.88
     anzunehmen
    0.85
     useRouter
    0.82
    Activations Density 0.018%

    No Known Activations