© 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. 83760
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
    reports
    -1.06
    notes
    -1.03
     inimes
    -0.96
    ｃ
    -0.96
     NOTES
    -0.94
     palju
    -0.94
     описание
    -0.93
    ounced
    -0.92
    noted
    -0.91
     melaporkan
    -0.90
    POSITIVE LOGITS
     said
    1.95
     op
    1.81
     felt
    1.66
     feels
    1.58
     while
    1.28
     pointed
    1.27
     feel
    1.19
     opinion
    1.19
     hoped
    1.14
     Feels
    1.14
    Activations Density 0.016%

    No Known Activations