© 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. 109906
    Prev
    Next
    INDEX
    Explanations

    participants rating or responding

    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
    。】
    -0.84
    agog
    -0.80
     automatiquement
    -0.79
    uccino
    -0.79
     Symp
    -0.77
    荤
    -0.77
     conclure
    -0.75
     Findings
    -0.75
    ಕ್ಕ
    -0.74
     Peri
    -0.72
    POSITIVE LOGITS
     rated
    1.79
     ratings
    1.67
     rating
    1.62
     responses
    1.55
     judgments
    1.43
     responded
    1.41
     answers
    1.31
     responds
    1.28
     answering
    1.27
     response
    1.25
    Activations Density 0.183%

    No Known Activations