© 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. 137558
    Prev
    Next
    INDEX
    Explanations

    merchandise searches

    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
    Negative Logits
    呚
    0.43
    ?’
    0.39
     म्ह
    0.38
     ঘোষিত
    0.38
    :”
    0.38
     элемента
    0.36
    icznego
    0.36
    ﺢ
    0.36
    ويم
    0.36
    NumConst
    0.36
    POSITIVE LOGITS
     Expertise
    0.40
    氖
    0.40
     दायरे
    0.37
    Validity
    0.37
     kari
    0.37
     Gallup
    0.36
     ATMs
    0.36
     isotopic
    0.35
    蟶
    0.35
     Stakes
    0.35
    Activations Density 0.000%

    No Known Activations