© 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. 22425
    Prev
    Next
    INDEX
    Explanations

    stringent quality, Dani Klein, Bayern Munich

    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
    er
    -2.84
     
    -2.75
     Referring
    -2.45
     Allowing
    -2.45
    y
    -2.33
     When
    -2.31
     Examining
    -2.31
    —
    -2.25
     Significantly
    -2.22
     Apparent
    -2.19
    POSITIVE LOGITS
    '
    3.27
    葑
    2.73
    CHREIB
    2.72
    of
    2.56
    
    2.52
    身的
    2.42
    讦
    2.41
     возможность
    2.39
    ouſ
    2.38
    稣
    2.31
    Activations Density 0.004%

    No Known Activations