© 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. 7227
    Prev
    Next
    INDEX
    Explanations

    to say the least

    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
     the
    -2.28
    んび
    -1.67
    </b>
    -1.67
     Still
    -1.55
    destroyAll
    -1.54
     Politiker
    -1.52
     &
    -1.49
    AllowAnonymous
    -1.47
     Always
    -1.46
     regardé
    -1.45
    POSITIVE LOGITS
    乄
    1.84
    the
    1.77
    ку
    1.75
    0
    1.72
    \
    1.71
     ſy
    1.67
    ков
    1.61
     SimpleName
    1.59
    ῞
    1.59
     grises
    1.53
    Activations Density 0.001%

    No Known Activations