© 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. 13771
    Prev
    Next
    INDEX
    Explanations

    population evolution

    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
    เรียก
    0.46
     เรียก
    0.45
    зывают
    0.42
    地图
    0.41
     ド
    0.41
     தன
    0.41
     frequented
    0.41
    エ
    0.41
    꼴
    0.41
    א
    0.40
    POSITIVE LOGITS
     był
    0.52
     było
    0.48
    ণে
    0.48
     była
    0.48
     yě
    0.46
     vardı
    0.46
     byly
    0.45
     neuropsych
    0.45
     wyk
    0.44
     bylo
    0.44
    Activations Density 0.009%

    No Known Activations