© 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. 112930
    Prev
    Next
    INDEX
    Explanations

    authors' last names

    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
    }$,
    -1.48
     naše
    -1.34
    Bibliografía
    -1.29
    .$.
    -1.28
    ála
    -1.27
    Viernes
    -1.25
    centerline
    -1.24
    fortune
    -1.23
    Our
    -1.23
     niektó
    -1.23
    POSITIVE LOGITS
     a
    1.22
     across
    1.16
    amp
    1.09
    </
    1.09
    1.08
    W
    1.08
     decides
    1.06
     oceano
    1.05
     видит
    1.05
     competes
    1.05
    Activations Density 0.320%

    No Known Activations