© 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. 44682
    Prev
    Next
    INDEX
    Explanations

    deposit

    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
    ed
    -3.02
    IN
    -3.02
    1
    -3.00
    as
    -2.94
    8
    -2.75
    an
    -2.72
    早已
    -2.70
    饜
    -2.69
    眼睛
    -2.67
    2
    -2.67
    POSITIVE LOGITS
    咵
    2.92
    相当于
    2.86
    ↵
    2.86
    焄
    2.84
    鋅
    2.80
    Donativos
    2.69
     всѣ
    2.64
     Ausland
    2.63
    鴣
    2.63
    狆
    2.61
    Activations Density 0.005%

    No Known Activations