© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40806
    Prev
    Next
    INDEX
    Explanations

    customer interaction, privacy features, or taxing rights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     корректи
    0.48
     व्यावहारिक
    0.47
    inę
    0.45
    গ্
    0.42
    Ը
    0.41
    здат
    0.41
    բ
    0.41
    ได้
    0.40
    ใด
    0.40
     какие
    0.40
    POSITIVE LOGITS
    ړه
    0.44
    wau
    0.42
    هرة
    0.42
    GoObject
    0.41
     Loew
    0.41
     bluish
    0.41
     ecz
    0.40
    ށ
    0.40
    يذ
    0.39
     pericol
    0.39
    Activations Density 0.001%

    No Known Activations