© 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. 125427
    Prev
    Next
    INDEX
    Explanations

    technical content and procedures

    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
     accountants
    0.42
     từng
    0.40
    ວ່າ
    0.38
    ગ
    0.38
    ㄞ
    0.38
    嵃
    0.37
     seseorang
    0.37
     sequentially
    0.37
     outwardly
    0.37
    aaaa
    0.36
    POSITIVE LOGITS
    Anast
    0.49
    跄
    0.47
     ピ
    0.45
    䢔
    0.45
    Publications
    0.44
     อา
    0.44
     Anast
    0.43
     วิชา
    0.42
    posti
    0.41
    Collectible
    0.41
    Activations Density 0.005%

    No Known Activations