© 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. 118726
    Prev
    Next
    INDEX
    Explanations

    as it is currently

    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
     复古
    -0.91
    GRAF
    -0.89
     때문에
    -0.82
    WARE
    -0.82
     kropp
    -0.82
    。)
    -0.82
    uksessa
    -0.82
     ennek
    -0.79
     voire
    -0.79
    hrens
    -0.79
    POSITIVE LOGITS
     pertains
    1.35
     relates
    1.29
     pertain
    1.21
     relate
    1.05
     existed
    1.05
     exists
    1.04
     Ihren
    0.92
     Did
    0.92
     progresses
    0.90
     stands
    0.89
    Activations Density 0.030%

    No Known Activations