© 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. 86221
    Prev
    Next
    INDEX
    Explanations

    words starting with Hist

    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
    ↵↵
    -3.67
     termasuk
    -2.56
     этот
    -2.33
    了他
    -2.31
     😀
    -2.30
    螓
    -2.25
    敺
    -2.23
    
    -2.22
    ⅅ
    -2.22
    …(
    -2.20
    POSITIVE LOGITS
    墻
    2.55
    mathrm
    2.47
     أيض
    2.45
    \
    2.42
    most
    2.34
    ally
    2.20
    蜴
    2.20
    as
    2.20
     '
    2.19
     发
    2.16
    Activations Density 0.020%

    No Known Activations