© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42389
    Prev
    Next
    INDEX
    Explanations

    quotation marks and code strings

    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
    \
    -2.66
    s
    -2.53
    mathrm
    -2.53
    !
    -2.52
    m
    -2.42
    ”.
    -2.41
    <td>
    -2.39
    猡
    -2.38
    푣
    -2.34
    焄
    -2.34
    POSITIVE LOGITS
    Ḧ
    2.63
    ンプー
    2.55
    —"
    2.52
    
    2.52
     IBRARY
    2.48
    ſu
    2.47
    媃
    2.45
    姌
    2.44
     "+
    2.42
     accentu
    2.38
    Activations Density 0.001%

    No Known Activations