© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 31295
    Prev
    Next
    INDEX
    Explanations

    class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     czynności
    0.67
    𝗯
    0.67
    ಸ್ಥ
    0.66
     connaissances
    0.65
     інші
    0.64
     footballers
    0.63
     footballer
    0.63
     букмекердик
    0.62
     மிகு
    0.60
     professores
    0.59
    POSITIVE LOGITS
    K
    1.07
    H
    0.90
    N
    0.89
    R
    0.87
    J
    0.86
    g
    0.85
    Q
    0.85
    U
    0.85
    G
    0.82
    F
    0.81
    Activations Density 0.001%

    No Known Activations