© 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. 84892
    Prev
    Next
    INDEX
    Explanations

    code or syntax

    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
     to
    -1.41
     tableta
    -1.38
     должны
    -1.32
     dimentic
    -1.27
     Its
    -1.27
     servire
    -1.27
    mapsto
    -1.26
    Если
    -1.25
    igslist
    -1.25
    Сле
    -1.23
    POSITIVE LOGITS
     of
    2.13
     from
    1.89
     this
    1.74
    </strong>
    1.73
     weißem
    1.59
    癡
    1.56
    </em>
    1.49
    暉
    1.47
    Legături
    1.46
     other
    1.41
    Activations Density 0.007%

    No Known Activations