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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30860
    Prev
    Next
    INDEX
    Explanations

    free software, Jan Op

    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
    一惊
    -1.19
    一愣
    -1.05
    见状
    -1.00
    下意识
    -0.94
     since
    -0.86
     Genova
    -0.84
    throated
    -0.84
    讶
    -0.83
    ={<
    -0.81
     Flüssigkeit
    -0.81
    POSITIVE LOGITS
     couldn
    1.28
     immediately
    1.13
     frowned
    1.10
     сразу
    1.07
     Couldn
    0.94
     instantly
    0.94
     felt
    0.93
     complexion
    0.91
     Immediately
    0.90
     unavoid
    0.90
    Activations Density 0.003%

    No Known Activations