© 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. 7670
    Prev
    Next
    INDEX
    Explanations

    not but rather than

    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
     även
    -1.36
     with
    -1.28
     (
    -1.24
    </b>
    -1.23
     include
    -1.22
    ——”
    -1.21
     such
    -1.20
    kgs
    -1.18
     also
    -1.17
    te
    -1.16
    POSITIVE LOGITS
     debería
    1.39
     Apenas
    1.39
    应该
    1.36
     pouze
    1.36
    而是
    1.33
     should
    1.33
     navegador
    1.32
    venez
    1.31
     deveria
    1.25
    bertura
    1.24
    Activations Density 0.079%

    No Known Activations