© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66348
    Prev
    Next
    INDEX
    Explanations

    signage, pigmentation, readership, eyewear, names

    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
    ar
    -2.56
     сможет
    -2.50
    —”
    -2.41
    樣的
    -2.34
     Jardín
    -2.33
    ⸒
    -2.33
     попыта
    -2.31
    ”
    -2.23
    ”—
    -2.22
    ing
    -2.19
    POSITIVE LOGITS
     were
    2.67
    璈
    2.55
     "
    2.39
    鸶
    2.38
     but
    2.25
    idjan
    2.25
     hacemos
    2.23
    рому
    2.19
     bout
    2.16
     signage
    2.06
    Activations Density 0.002%

    No Known Activations