© 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. 22-GEMMASCOPE-RES-131K
    7. 26239
    Prev
    Next
    INDEX
    Explanations

    company logos

    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
     But
    -2.52
     algún
    -2.47
    ].
    -2.23
    that
    -2.23
    at
    -2.23
    S
    -2.22
     you
    -2.14
    尛
    -2.08
    *.
    -2.08
    ING
    -2.08
    POSITIVE LOGITS
    '
    2.58
    欒
    2.48
     wth
    2.30
     péché
    2.19
     作り方
    2.16
     inesperado
    2.14
     rígido
    2.08
    𖣘
    2.06
    闺蜜
    2.06
    过于
    2.05
    Activations Density 0.008%

    No Known Activations