© 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. 40-GEMMASCOPE-2-RES-262K
    7. 215356
    Prev
    Next
    INDEX
    Explanations

    lower costs

    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
    थुरा
    0.43
    iają
    0.42
    诰
    0.42
    ్రమ
    0.40
    핞
    0.40
     ერთი
    0.39
    ্বাদ
    0.39
     Gaut
    0.39
    स्वा
    0.39
    啮
    0.39
    POSITIVE LOGITS
     x
    0.41
    更好的
    0.41
     shatter
    0.41
     х
    0.39
    tennis
    0.39
    Distance
    0.38
     теннис
    0.38
     डिस्टेंस
    0.38
    庆
    0.37
     detect
    0.37
    Activations Density 0.004%

    No Known Activations