© 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. 46451
    Prev
    Next
    INDEX
    Explanations

    reports, investigations, or issues

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

    command descriptions or definitions

    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
    匠
    0.46
     kyun
    0.41
    ায়
    0.40
    नाथ
    0.40
     viewed
    0.39
     eût
    0.39
    StringIO
    0.39
    ambia
    0.38
     modelled
    0.38
     Счет
    0.38
    POSITIVE LOGITS
    ar
    0.56
    r
    0.55
    nicht
    0.46
    e
    0.46
     الإ
    0.45
     отказаться
    0.45
     ない
    0.45
     Nicht
    0.45
     नव्हते
    0.43
    الأ
    0.42
    Activations Density 0.000%

    No Known Activations