© 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. 22-GEMMASCOPE-RES-131K
    7. 72176
    Prev
    Next
    INDEX
    Explanations

    candle and wax items

    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_22/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
     alguns
    -2.78
     abſ
    -2.44
    熥
    -2.41
     fabulous
    -2.41
    樒
    -2.38
     unbelievably
    -2.34
     extremely
    -2.33
    
    -2.31
     incredibly
    -2.30
     ſever
    -2.30
    POSITIVE LOGITS
     With
    2.95
    With
    2.67
    When
    2.55
    Nearly
    2.53
    During
    2.47
    Almost
    2.45
     Nearly
    2.36
     sparked
    2.36
    Shortly
    2.34
     Trying
    2.33
    Activations Density 0.005%

    No Known Activations