© 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. 93867
    Prev
    Next
    INDEX
    Explanations

    incumbent

    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
    fazione
    -0.84
     savag
    -0.78
    headset
    -0.77
    unting
    -0.77
     bilden
    -0.76
     visitors
    -0.75
    amentul
    -0.74
    rifts
    -0.73
     réception
    -0.72
     admirers
    -0.72
    POSITIVE LOGITS
     incumbent
    6.31
     incumb
    5.09
     Inc
    3.58
    inc
    3.50
    Inc
    3.42
     inc
    2.75
    umbent
    2.72
     incubation
    2.34
    INC
    2.30
     INC
    2.30
    Activations Density 0.080%

    No Known Activations