© 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. 118855
    Prev
    Next
    INDEX
    Explanations

    DROP TABLE IF EXISTS

    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
    ごとに
    -0.78
    ⛸
    -0.75
     somewhat
    -0.75
    方面的
    -0.74
     tory
    -0.72
    wtf
    -0.71
     studded
    -0.70
     коммуна
    -0.70
    鋲
    -0.69
    ングル
    -0.68
    POSITIVE LOGITS
     Drop
    0.97
    Drop
    0.84
     DROP
    0.83
     зах
    0.82
    ittäin
    0.79
     prawidł
    0.77
     angeb
    0.77
     pedag
    0.75
     residue
    0.75
     spill
    0.75
    Activations Density 0.013%

    No Known Activations