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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168764
    Prev
    Next
    INDEX
    Explanations

    basis and comparison point

    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
    用到
    0.51
    居
    0.43
    වත්
    0.42
     goes
    0.41
    رفته
    0.40
     links
    0.40
     مشرف
    0.39
    ใส่
    0.39
    bollah
    0.39
    зиден
    0.38
    POSITIVE LOGITS
     odby
    0.42
     erfolgte
    0.40
     据
    0.39
     étr
    0.39
     شناخته
    0.39
    每年
    0.38
     пыта
    0.38
     senare
    0.38
     め
    0.38
     versucht
    0.38
    Activations Density 0.025%

    No Known Activations