© 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-65K
    7. 5060
    Prev
    Next
    INDEX
    Explanations

    have been trained or have knowledge

    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_65k_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
     been
    0.41
    䄪
    0.39
     ایک
    0.38
     heeft
    0.36
    棹
    0.36
     हैज
    0.35
     stata
    0.35
     problemler
    0.35
    ־
    0.35
     problemen
    0.35
    POSITIVE LOGITS
    op
    0.45
    er
    0.44
    id
    0.41
    il
    0.40
    ographics
    0.39
    as
    0.38
    os
    0.38
    ar
    0.36
    én
    0.36
    at
    0.35
    Activations Density 0.039%

    No Known Activations