© 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. 45302
    Prev
    Next
    INDEX
    Explanations

    prefixes ther- and therewith

    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
    的
    -2.44
    也
    -2.38
     приготовить
    -2.19
    r
    -2.19
    X
    -2.17
    は
    -2.14
     icona
    -2.13
     et
    -2.13
    "
    -2.08
     để
    -2.06
    POSITIVE LOGITS
    ”.
    2.88
     to
    2.25
    ;
    2.17
    轳
    2.08
    xvii
    2.06
    珢
    1.91
    graduate
    1.89
    xii
    1.84
    xiii
    1.84
    凪
    1.83
    Activations Density 0.000%

    No Known Activations