© 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. 85471
    Prev
    Next
    INDEX
    Explanations

    examples of such

    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
     This
    -2.77
    ⚋
    -2.48
    ing
    -2.20
     decisões
    -2.19
    rierten
    -2.16
     請
    -2.13
    درسة
    -2.11
    ைகள்
    -2.11
     dovr
    -2.11
     It
    -2.11
    POSITIVE LOGITS
    .
    2.70
    0
    2.30
    ’
    2.22
    1
    2.19
     voor
    2.19
     “
    2.13
    ‘
    2.03
    瘓
    1.98
    “
    1.98
     Vordergrund
    1.91
    Activations Density 0.001%

    No Known Activations