© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133501
    Prev
    Next
    INDEX
    Explanations

    manipulating symbols

    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_40_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
    ）』
    0.43
    ことがある
    0.43
    中間
    0.40
    縮
    0.40
    stop
    0.38
    imam
    0.38
     Chur
    0.36
    ㆍ
    0.36
    絫
    0.36
     (')
    0.36
    POSITIVE LOGITS
     බ
    0.41
     cattle
    0.40
     calligraphy
    0.40
     ovens
    0.38
    
    0.38
     artisanal
    0.38
     getContentPane
    0.37
    葆
    0.36
     goat
    0.36
     analysed
    0.36
    Activations Density 0.001%

    No Known Activations