© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110760
    Prev
    Next
    INDEX
    Explanations

    reasons given

    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
     Confirmed
    -0.85
     confirme
    -0.83
     ориги
    -0.80
    confirmed
    -0.79
     Ona
    -0.77
    Confirmed
    -0.76
     Confirm
    -0.75
     hvor
    -0.75
    确认
    -0.74
    잖
    -0.74
    POSITIVE LOGITS
     reasons
    5.56
     reason
    4.25
    reasons
    4.22
     Reasons
    4.16
    Reasons
    4.09
    理由
    3.95
    reason
    3.55
    Reason
    3.55
     reasoning
    3.53
     REASONS
    3.30
    Activations Density 0.067%

    No Known Activations