© 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. 220219
    Prev
    Next
    INDEX
    Explanations

    last couple, star rating, closing in, ice cream

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

    diagnostics, maps, favorite activities

    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
    sterreich
    0.49
    䉍
    0.45
     rá
    0.45
     කියලා
    0.44
     '
    0.44
     ₹
    0.43
     Rogers
    0.43
     '$
    0.42
     wann
    0.42
    slash
    0.42
    POSITIVE LOGITS
    Conclusions
    0.52
    Name
    0.50
     πριν
    0.50
    eae
    0.50
    ুকু
    0.48
    Skip
    0.48
    谨慎
    0.47
    Specification
    0.46
    బడు
    0.45
    ReadAll
    0.45
    Activations Density 0.000%

    No Known Activations