© 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. 102422
    Prev
    Next
    INDEX
    Explanations

    wishes and good tidings

    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
    啣
    -2.19
    
    -2.16
    　　「
    -2.13
    }/>
    -2.06
    翃
    -2.03
     OGSÅ
    -1.95
     ilumina
    -1.93
     INFORMACIÓN
    -1.90
     you
    -1.88
    縠
    -1.88
    POSITIVE LOGITS
    “
    2.19
    5
    2.16
    a
    2.14
    7
    2.03
    6
    1.96
    4
    1.95
     of
    1.80
    d
    1.79
     innehå
    1.79
     ändå
    1.77
    Activations Density 0.001%

    No Known Activations