© 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. 128100
    Prev
    Next
    INDEX
    Explanations

    proper names

    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
    ꜆
    -3.19
    nessy
    -3.13
    
    -2.97
    恹
    -2.81
    
    -2.73
    屨
    -2.73
     existem
    -2.70
    ︕
    -2.67
     THERE
    -2.56
     they
    -2.55
    POSITIVE LOGITS
    $
    3.61
    '
    2.83
    a
    2.67
    1
    2.50
    _{
    2.42
    }
    2.41
    V
    2.36
    N
    2.31
    2
    2.27
    B
    2.25
    Activations Density 0.007%

    No Known Activations