© 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. 68108
    Prev
    Next
    INDEX
    Explanations

    regulated output

    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
     who
    -2.27
     już
    -1.54
    $
    -1.53
     Already
    -1.50
    {~
    -1.48
    providedIn
    -1.48
    早已
    -1.48
     similaires
    -1.41
     می‌ده
    -1.41
    </i>
    -1.40
    POSITIVE LOGITS
    在这种
    1.31
    因为他
    1.27
    OBJET
    1.27
     電気
    1.27
    ऍ
    1.25
    랗
    1.24
     they
    1.24
    上がり
    1.21
    在這
    1.20
     mereka
    1.20
    Activations Density 0.228%

    No Known Activations