© 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. 14316
    Prev
    Next
    INDEX
    Explanations

    words joined by and

    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
     هذه
    -1.46
    nachron
    -1.27
     voyez
    -1.23
    尤其
    -1.21
    на
    -1.20
    这些
    -1.19
    ه
    -1.19
     ktoś
    -1.16
     wieder
    -1.14
     Eugène
    -1.14
    POSITIVE LOGITS
     dritte
    1.33
    แรก
    1.30
    ︓
    1.30
     المعيار
    1.29
     cierta
    1.27
    //});
    1.26
    昰
    1.25
    ',
    1.25
     a
    1.24
    常见的
    1.23
    Activations Density 0.086%

    No Known Activations