© 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. 43558
    Prev
    Next
    INDEX
    Explanations

    orderly arrays or transverse momentum

    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
    .
    -3.47
    <bos>
    -2.83
    s
    -2.81
     gewor
    -2.28
    𞤤
    -2.23
     Übergang
    -2.19
     dunklen
    -2.16
     steigen
    -2.13
     Gedanke
    -2.08
    无比
    -2.05
    POSITIVE LOGITS
    呖
    2.81
    辚
    2.78
    攆
    2.67
    磲
    2.66
    Ꮄ
    2.50
    </strong>
    2.45
    溦
    2.45
    氿
    2.39
    愃
    2.36
    ኾ
    2.36
    Activations Density 0.008%

    No Known Activations