© 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. 113808
    Prev
    Next
    INDEX
    Explanations

    Mey, Meyers, Şahin, Brookings

    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
    $
    -3.42
    );
    -2.97
    with
    -2.77
    0
    -2.64
    ↵↵
    -2.50
    2
    -2.44
    袮
    -2.38
    >=
    -2.19
    }$
    -2.13
    1
    -2.09
    POSITIVE LOGITS
     \"
    3.23
    臜
    3.00
    橚
    2.66
    穑
    2.61
    出了一
    2.55
    はその
    2.50
     famosos
    2.48
    嫱
    2.38
     Which
    2.33
     semblent
    2.33
    Activations Density 0.002%

    No Known Activations