© 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. 84771
    Prev
    Next
    INDEX
    Explanations

    even though

    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
     database
    0.48
     con
    0.45
     Island
    0.44
     v
    0.44
    un
    0.43
    ew
    0.43
     question
    0.43
     where
    0.43
     website
    0.42
     unit
    0.42
    POSITIVE LOGITS
    的他
    0.46
    aunque
    0.45
    довать
    0.45
    дра
    0.44
    ICY
    0.44
     долго
    0.44
     λόγω
    0.44
     мати
    0.43
    За
    0.43
    ｾ
    0.42
    Activations Density 0.008%

    No Known Activations