© 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. 34795
    Prev
    Next
    INDEX
    Explanations

    many things

    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
     ਅ
    0.43
    רי
    0.42
     dahin
    0.42
     će
    0.42
    នឹង
    0.41
    מת
    0.40
    }.$$
    0.40
     هت
    0.39
    અ
    0.39
    א
    0.39
    POSITIVE LOGITS
    থেষ্ট
    0.41
     albeit
    0.40
     العديد
    0.39
    rograph
    0.39
     thậm
    0.38
    QRCode
    0.38
     standing
    0.38
     oftentimes
    0.38
     знамени
    0.37
     fared
    0.37
    Activations Density 0.011%

    No Known Activations