© 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. 22-GEMMASCOPE-RES-131K
    7. 65049
    Prev
    Next
    INDEX
    Explanations

    physical and mathematical units

    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_22/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
    以上です
    -2.06
    鷽
    -1.79
    dekat
    -1.77
    ❢
    -1.72
    hadapi
    -1.70
    いかがでしたか
    -1.68
    และ
    -1.66
    Зно
    -1.63
     یا
    -1.60
    Klub
    -1.58
    POSITIVE LOGITS
    la
    2.22
    re
    2.06
    se
    1.90
    of
    1.86
    та
    1.84
     '
    1.81
    us
    1.77
    ne
    1.77
    an
    1.73
    lo
    1.71
    Activations Density 0.003%

    No Known Activations