© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 56899
    Prev
    Next
    INDEX
    Explanations

    I want to or I [action]

    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
     reeks
    0.49
    regen
    0.47
     Brexit
    0.47
    .');
    0.46
     oedd
    0.45
     rong
    0.45
     sendo
    0.45
     kini
    0.45
     chegou
    0.45
    edi
    0.44
    POSITIVE LOGITS
     열심히
    0.46
    编码
    0.44
    보다는
    0.43
    检查
    0.42
    教师
    0.42
    𝙥
    0.42
    하지만
    0.41
    蛋白质
    0.41
    Basketball
    0.41
    说说
    0.40
    Activations Density 0.004%

    No Known Activations