© 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. 71015
    Prev
    Next
    INDEX
    Explanations

    words following brackets

    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
     are
    -1.90
    "
    -1.70
    ve
    -1.61
    );
    -1.53
    m
    -1.46
    We
    -1.41
     نظر
    -1.41
    :
    -1.38
    了一
    -1.31
     самых
    -1.28
    POSITIVE LOGITS
     выборе
    1.64
    氛围
    1.62
    länger
    1.55
    ⃨
    1.53
    garve
    1.49
    𝑟
    1.48
     clicar
    1.46
    jącego
    1.45
     знал
    1.45
     \
    1.44
    Activations Density 0.113%

    No Known Activations