© 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. 113685
    Prev
    Next
    INDEX
    Explanations

    providing something

    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
    y
    -2.97
    e
    -2.50
    是
    -2.45
    ៚
    -2.41
    z
    -2.39
    风
    -2.17
     χρησιμοποι
    -2.16
    自
    -2.14
    他
    -2.13
    ↵
    -2.11
    POSITIVE LOGITS
    葙
    2.73
    蠃
    2.73
    姈
    2.58
    聍
    2.58
    艄
    2.50
     erstes
    2.42
    蠓
    2.39
     evocative
    2.31
    へ行
    2.31
     creando
    2.31
    Activations Density 0.009%

    No Known Activations