© 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. 128599
    Prev
    Next
    INDEX
    Explanations

    categories and descriptions

    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
     gemeenten
    -1.72
    為に
    -1.72
    にします
    -1.50
    に入れる
    -1.48
    の準備
    -1.46
    begins
    -1.41
    ところに
    -1.41
    さぁ
    -1.40
     derni
    -1.38
    gebraucht
    -1.38
    POSITIVE LOGITS
    と
    1.81
    があります
    1.74
    がある
    1.71
     (
    1.66
     как
    1.58
    もある
    1.52
    を
    1.49
    ですが
    1.43
    があり
    1.39
    があるので
    1.38
    Activations Density 0.013%

    No Known Activations