© 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. 126874
    Prev
    Next
    INDEX
    Explanations

    parts of speech and relations

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

    html body tag

    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
    たちの
    0.46
    %$
    0.43
     concede
    0.43
     nasty
    0.43
     चुनाव
    0.42
    esity
    0.41
    ש
    0.41
     foule
    0.41
    с
    0.41
     refute
    0.40
    POSITIVE LOGITS
     originalmente
    0.50
     изначально
    0.48
     RouterModule
    0.45
    গতকাল
    0.43
     étapes
    0.43
     তৎকালীন
    0.42
     étaient
    0.41
     Assuming
    0.41
     Bind
    0.41
     গতকাল
    0.41
    Activations Density 0.000%

    No Known Activations