© 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. 10-GEMMASCOPE-RES-131K
    7. 129080
    Prev
    Next
    INDEX
    Explanations

    more info

    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_10/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
    
    -2.73
    sukienka
    -2.61
    蟥
    -2.59
    皤
    -2.52
    焄
    -2.45
     baumwolle
    -2.38
    苌
    -2.38
    锖
    -2.33
    砣
    -2.30
    頎
    -2.30
    POSITIVE LOGITS
    5
    3.20
     If
    2.56
    6
    2.53
    7
    2.48
    Not
    2.45
    All
    2.44
    One
    2.25
    To
    2.25
    Only
    2.25
     info
    2.20
    Activations Density 0.006%

    No Known Activations