© 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. 111112
    Prev
    Next
    INDEX
    Explanations

    born of

    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
     quelque
    0.49
     situazioni
    0.46
    힐
    0.45
     alguma
    0.44
    Με
    0.43
     qualche
    0.42
     այ
    0.41
    ရှင်း
    0.41
     बंगाल
    0.41
    Mình
    0.39
    POSITIVE LOGITS
     ២
    0.46
     ٢
    0.44
     २०
    0.44
     экономической
    0.43
    ി
    0.43
    ود
    0.43
    ตาย
    0.42
    ៧
    0.42
     فشار
    0.41
    fono
    0.41
    Activations Density 0.006%

    No Known Activations