© 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. 16-GEMMASCOPE-2-RES-262K
    7. 1339
    Prev
    Next
    INDEX
    Explanations

    conditional actions and results

    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_16_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
    ،
    0.39
     putea
    0.30
     l
    0.29
     must
    0.29
     country
    0.29
    ri
    0.29
     factor
    0.29
    с
    0.29
     spectacle
    0.29
     mountains
    0.28
    POSITIVE LOGITS
    اً
    0.39
    𓏧
    0.34
    ين
    0.34
    涑
    0.34
    跻
    0.34
    تع
    0.33
    િન
    0.32
    駋
    0.32
    <unused569>
    0.32
    تون
    0.31
    Activations Density 4.522%

    No Known Activations