© 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. 101394
    Prev
    Next
    INDEX
    Explanations

    words starting with Bra

    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
    ſſel
    -2.89
    菹
    -2.77
    新能源
    -2.73
    鲠
    -2.73
    猡
    -2.72
    怎么回事
    -2.70
    踽
    -2.67
    廰
    -2.64
    槼
    -2.61
    pecabe
    -2.55
    POSITIVE LOGITS
    3
    4.03
    2
    3.92
    1
    3.61
    4
    3.48
    ?
    3.44
    =
    3.33
    6
    3.25
    _
    3.13
    <
    3.09
    7
    3.08
    Activations Density 0.005%

    No Known Activations