© 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. 109909
    Prev
    Next
    INDEX
    Explanations

    family and relationships

    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
     superhuman
    -0.96
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -0.91
     dauert
    -0.86
    vité
    -0.84
     compatri
    -0.84
    ğiniz
    -0.84
     później
    -0.83
     visco
    -0.82
     cytoplas
    -0.82
    ativis
    -0.82
    POSITIVE LOGITS
     successful
    1.74
    successful
    1.65
    Successful
    1.35
     Successful
    1.31
     success
    1.22
     succès
    1.15
     career
    1.12
    Successfully
    1.09
     recently
    1.05
     éxito
    1.05
    Activations Density 0.057%

    No Known Activations