© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 12785
    Prev
    Next
    INDEX
    Explanations

    items and brands

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isset
    0.50
    '`
    0.50
     масте
    0.47
    pies
    0.46
    Salam
    0.46
    assisted
    0.46
    pth
    0.46
     assisted
    0.45
    _{+}-
    0.45
    Conclusions
    0.45
    POSITIVE LOGITS
    これが
    0.73
     pads
    0.66
    這是
    0.59
     nécess
    0.59
     tubs
    0.58
    Tub
    0.57
     fout
    0.56
     Allison
    0.56
     tuleb
    0.56
     dah
    0.55
    Activations Density 0.000%

    No Known Activations