© 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. 127876
    Prev
    Next
    INDEX
    Explanations

    search queries and identifiers

    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
     fubject
    -1.58
     thoſe
    -1.55
     neceffary
    -1.48
     occafion
    -1.46
    😠
    -1.45
     mahu
    -1.42
    🤬
    -1.41
     dacia
    -1.40
     yaka
    -1.39
     uye
    -1.33
    POSITIVE LOGITS
     ofrecerte
    1.60
    职位
    1.53
     ayudarte
    1.52
     "..\..\..\
    1.45
    pgfplots
    1.40
     hornear
    1.38
    cribes
    1.38
    Possui
    1.37
     italienischen
    1.34
     после
    1.32
    Activations Density 0.034%

    No Known Activations