© 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. 160363
    Prev
    Next
    INDEX
    Explanations

    event or accomplishment

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

    describing authorial intent/approach

    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
     уйна
    0.49
    ână
    0.49
    ныгы
    0.49
     বাক্য
    0.48
    ăți
    0.47
    рсә
    0.46
    ୟ
    0.46
    Schools
    0.46
    Soccer
    0.45
    settes
    0.45
    POSITIVE LOGITS
     لما
    0.45
     neer
    0.44
     مدى
    0.43
     might
    0.43
     dik
    0.43
     Leverkusen
    0.43
     rarity
    0.42
     Indigenous
    0.41
     Excise
    0.41
    _\
    0.41
    Activations Density 0.000%

    No Known Activations