© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 103513
    Prev
    Next
    INDEX
    Explanations

    already, raised

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ፏ
    0.42
    to
    0.41
    b
    0.38
    ran
    0.37
     Llan
    0.36
    pos
    0.36
    erville
    0.35
    AFP
    0.35
    pt
    0.34
    h
    0.34
    POSITIVE LOGITS
    創造
    0.44
     sprayer
    0.42
    クサ
    0.42
    خل
    0.41
     inoxydable
    0.41
    槨
    0.40
     améliorer
    0.40
    創新
    0.39
    椏
    0.39
    充電
    0.39
    Activations Density 0.003%

    No Known Activations