© 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. 112395
    Prev
    Next
    INDEX
    Explanations

    consulting practice and services

    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
    section
    -2.56
    e
    -2.52
     cette
    -2.44
     lorsque
    -2.42
    ſu
    -2.36
     we
    -2.34
    amir
    -2.27
     was
    -2.17
     necesario
    -2.14
    后
    -2.14
    POSITIVE LOGITS
    葙
    3.45
    ).
    2.95
    ."
    2.84
    酲
    2.63
    .</
    2.61
    }*/
    2.50
    The
    2.45
    ].
    2.33
    ڧ
    2.31
    ～～
    2.30
    Activations Density 0.004%

    No Known Activations