© 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. 128228
    Prev
    Next
    INDEX
    Explanations

    @memberOf _

    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
    </h3>
    -2.22
     थे
    -2.14
     grüne
    -2.03
     empêche
    -1.92
     је
    -1.88
    erder
    -1.84
    ladung
    -1.78
     ДА
    -1.77
    下意识
    -1.75
     serão
    -1.74
    POSITIVE LOGITS
    L
    2.59
    S
    2.36
    R
    2.25
    memberof
    2.23
    齶
    2.22
     deine
    2.11
    D
    2.08
    M
    2.06
     ۷
    2.03
    N
    2.03
    Activations Density 0.002%

    No Known Activations