© 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. 71699
    Prev
    Next
    INDEX
    Explanations

    days of the week and dates

    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
     această
    -1.32
     procéder
    -1.27
     durante
    -1.19
    就直接
    -1.17
     vinos
    -1.16
    镞
    -1.16
    从来没有
    -1.15
    vities
    -1.14
     când
    -1.13
     peluche
    -1.12
    POSITIVE LOGITS
     vedno
    1.38
    万一
    1.34
    忸
    1.30
    rò
    1.23
     that
    1.23
     connotation
    1.23
    :
    1.22
     with
    1.20
     greats
    1.17
     gratuitos
    1.16
    Activations Density 0.187%

    No Known Activations