© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69761
    Prev
    Next
    INDEX
    Explanations

    priority is claimed or order is

    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
    Dividend
    -1.44
    он
    -1.43
    entown
    -1.27
    小
    -1.26
    т
    -1.25
    </table>
    -1.25
    FONTE
    -1.24
    रा
    -1.23
    הו
    -1.23
    ở
    -1.23
    POSITIVE LOGITS
     those
    1.94
     these
    1.84
    というわけで
    1.67
    Those
    1.67
     actually
    1.63
    These
    1.59
    While
    1.55
    ＝＝＝＝
    1.55
    さっそく
    1.50
     what
    1.48
    Activations Density 0.069%

    No Known Activations