© 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. 45112
    Prev
    Next
    INDEX
    Explanations

    assignments and function definitions

    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
    Schule
    -1.77
    bande
    -1.48
     mangiare
    -1.46
    罴
    -1.45
    Waga
    -1.42
    あなたは
    -1.41
    私たちは
    -1.37
    banden
    -1.35
    Funktionen
    -1.35
     estómago
    -1.35
    POSITIVE LOGITS
    将
    1.67
    \
    1.47
    (
    1.44
    和
    1.44
    可能
    1.42
    D
    1.41
    にゃ
    1.41
     –
    1.41
    =
    1.38
    を行
    1.34
    Activations Density 0.026%

    No Known Activations