© 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. 86215
    Prev
    Next
    INDEX
    Explanations

    compose essay

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

    lists of platforms and methods

    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
     ইমন
    0.48
    more
    0.46
    mores
    0.46
    you
    0.43
    ]).
    0.43
     you
    0.41
    rels
    0.40
    ekten
    0.40
    ê
    0.40
    ).\
    0.40
    POSITIVE LOGITS
     وانا
    0.52
     WUE
    0.51
    授業
    0.45
     banco
    0.44
     Rydberg
    0.44
     Exchequer
    0.44
     電気
    0.43
    പ്പെട്ട
    0.43
    setminus
    0.43
     compt
    0.42
    Activations Density 0.001%

    No Known Activations