© 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. 68215
    Prev
    Next
    INDEX
    Explanations

    pub/ or pool/

    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
    }$,
    -1.53
     היא
    -1.50
     она
    -1.47
     teórico
    -1.34
     decorativo
    -1.33
    )$,
    -1.32
     krás
    -1.30
     точки
    -1.29
    ":[{
    -1.27
    ссию
    -1.27
    POSITIVE LOGITS
    alties
    1.84
     between
    1.65
    tellers
    1.64
    himself
    1.48
    considered
    1.48
     his
    1.44
    classed
    1.41
    zied
    1.41
    included
    1.39
    obtained
    1.38
    Activations Density 0.005%

    No Known Activations