© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 113499
    Prev
    Next
    INDEX
    Explanations

    black box systems or incorrect calculations

    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
    ’
    0.50
     리뷰
    0.46
    Attachment
    0.43
     في
    0.43
    Interrupt
    0.43
     سنا
    0.42
     نفسي
    0.42
     ይህ
    0.41
     داخل
    0.40
     مداخل
    0.40
    POSITIVE LOGITS
    ogène
    0.48
    ᑉ
    0.48
     organizations
    0.48
    ジン
    0.48
    آور
    0.48
    க
    0.47
    ᙱ
    0.47
    akai
    0.46
    ၻ
    0.46
    ylmethylsulfanyl
    0.46
    Activations Density 0.006%

    No Known Activations