© 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. 25966
    Prev
    Next
    INDEX
    Explanations

    xml namespace or tag closing

    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
    diator
    -1.02
    嗒
    -1.01
     Präsentation
    -0.97
     their
    -0.93
     Kooperation
    -0.92
     Beitrag
    -0.90
    WEBPACK
    -0.90
    mido
    -0.87
    tya
    -0.86
    lorious
    -0.86
    POSITIVE LOGITS
    Agen
    1.26
     nogal
    1.15
    綃
    1.13
     hybride
    1.12
    نے
    1.12
    踅
    1.11
     asma
    1.11
     rente
    1.09
     maniere
    1.06
     tinte
    1.05
    Activations Density 0.008%

    No Known Activations