© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    I know

    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
     よく
    0.45
    '.
    0.37
    しましょう
    0.37
     appropriately
    0.36
     youll
    0.36
     これ
    0.36
    你们
    0.36
    ৎ
    0.36
     wisely
    0.35
    ').
    0.35
    POSITIVE LOGITS
    あくまで
    0.49
     azért
    0.47
    adece
    0.46
     justement
    0.46
     именно
    0.45
    otros
    0.44
    所以我
    0.44
     falei
    0.42
    porque
    0.41
    那位
    0.40
    Activations Density 0.030%

    No Known Activations