© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 151327
    Prev
    Next
    INDEX
    Explanations

    free offers and conditions

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

    visa type

    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
     гораздо
    0.47
     मुसी
    0.44
     недостаточно
    0.44
     скорее
    0.44
    któ
    0.43
     কীভাবে
    0.43
    可能会
    0.43
    ⛷
    0.43
    ष्ठ
    0.42
    挑战
    0.42
    POSITIVE LOGITS
     all
    0.53
     alluvial
    0.47
     كلهم
    0.47
     всіх
    0.47
    所有的
    0.47
     gratuits
    0.46
     taux
    0.46
     antal
    0.46
     spins
    0.46
     semua
    0.45
    Activations Density 0.003%

    No Known Activations