© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 14211
    Prev
    Next
    INDEX
    Explanations

    in place, on the go, at rest, in the art

    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_22/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
     Benutz
    -1.42
    Vlast
    -1.38
     liście
    -1.34
     będziemy
    -1.20
     bedeut
    -1.20
    嫒
    -1.19
    [];
    -1.19
    moncler
    -1.16
     fattori
    -1.16
     interesting
    -1.14
    POSITIVE LOGITS
    </strong>
    1.38
    ,
    1.37
    i
    1.28
     /
    1.27
    ocity
    1.20
     miscon
    1.17
     katk
    1.17
     pleasures
    1.16
     crunchy
    1.16
    菠
    1.13
    Activations Density 0.082%

    No Known Activations