© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 41392
    Prev
    Next
    INDEX
    Explanations

    Nick and Sally how

    np_acts-logits-general · gemini-2.5-flash-lite

    destiny, spirit, versions, family, atoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    До
    0.56
    0
    0.54
    DE
    0.53
    У
    0.52
    Mp
    0.50
    SD
    0.50
    EIN
    0.49
    U
    0.49
    Guides
    0.48
    E
    0.48
    POSITIVE LOGITS
     destino
    0.50
     lá
    0.49
     brillantes
    0.47
     membr
    0.46
     deaktiv
    0.46
     sencillo
    0.45
     átomos
    0.44
     abandonar
    0.44
     thánh
    0.43
     templo
    0.43
    Activations Density 0.000%

    No Known Activations