© 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. 127709
    Prev
    Next
    INDEX
    Explanations

    start of words

    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
     "--
    -1.52
    ȼ
    -1.43
     этом
    -1.43
    ﺅ
    -1.41
    了出去
    -1.41
    はこの
    -1.34
    adakan
    -1.33
     этому
    -1.31
     "]
    -1.31
    dienne
    -1.30
    POSITIVE LOGITS
     to
    1.70
     is
    1.44
    ,
    1.41
     with
    1.37
     successive
    1.23
     all
    1.23
     are
    1.22
     down
    1.22
     without
    1.21
    :
    1.21
    Activations Density 0.022%

    No Known Activations