© 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. 72411
    Prev
    Next
    INDEX
    Explanations

    upstream location, client, side

    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
    0
    -3.17
    7
    -3.09
    -2.95
    4
    -2.67
    1
    -2.59
    3
    -2.45
    ーー
    -2.39
     eigentliche
    -2.38
     beberapa
    -2.38
     alguns
    -2.36
    POSITIVE LOGITS
    s
    2.69
    ی
    2.58
     ⓒ
    2.33
    \
    2.19
    ↵↵
    2.17
     trainee
    2.13
     lambat
    2.11
    íba
    2.09
    族的
    2.09
     stylish
    2.09
    Activations Density 0.005%

    No Known Activations