© 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. 84793
    Prev
    Next
    INDEX
    Explanations

    directing to URLs or further details

    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
    罍
    -2.42
    vânt
    -1.70
     帅气
    -1.70
     花纹
    -1.67
     loob
    -1.66
    錾
    -1.66
     cirugía
    -1.65
    秾
    -1.63
    initiate
    -1.57
     quinze
    -1.55
    POSITIVE LOGITS
     for
    3.31
    0
    2.22
    9
    2.09
    5
    2.03
    8
    1.92
     to
    1.85
    4
    1.82
    k
    1.81
     also
    1.70
    7
    1.69
    Activations Density 0.019%

    No Known Activations