© 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. 143895
    Prev
    Next
    INDEX
    Explanations

    review starters like "Okay" or "Right"

    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
     shin
    0.39
    די
    0.38
    ってる
    0.38
    𝙶
    0.38
    recruit
    0.37
    🤣
    0.36
    لون
    0.36
    이죠
    0.35
    ැන
    0.35
     डोनाल्ड
    0.35
    POSITIVE LOGITS
     Forschung
    0.44
    ৗ
    0.42
     البيانات
    0.41
     پڑھی
    0.41
     beschrieben
    0.41
    舟
    0.39
    空気
    0.39
     analytical
    0.38
    .}}
    0.38
     addBook
    0.38
    Activations Density 0.003%

    No Known Activations