© 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. 13788
    Prev
    Next
    INDEX
    Explanations

    names and 'abc'

    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
    ?”
    -2.56
    上官
    -2.42
    (),
    -2.34
     midway
    -2.31
    蒟
    -2.28
     ehemal
    -2.23
    ꠥ
    -2.22
     poniendo
    -2.14
    नलोड
    -2.14
     presentó
    -2.14
    POSITIVE LOGITS
    儅
    2.95
    ers
    2.83
    沵
    2.66
    饜
    2.63
    g
    2.52
    z
    2.48
    霂
    2.42
     菇
    2.41
    ܆
    2.38
    x
    2.34
    Activations Density 0.033%

    No Known Activations