© 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. 716
    Prev
    Next
    INDEX
    Explanations

    animal facts

    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
     نشرح
    0.38
    নিউ
    0.38
    сында
    0.37
    த்திலிருந்து
    0.37
    は見
    0.35
     समीकरण
    0.35
     создании
    0.34
     académica
    0.34
    <(),
    0.34
     latérales
    0.34
    POSITIVE LOGITS
    ences
    0.41
     जानवरों
    0.39
     जानवर
    0.36
     एनिमल
    0.36
     Esperanza
    0.36
     vertebrates
    0.35
    RELATED
    0.35
     Hallmark
    0.35
    animals
    0.34
    Mamm
    0.34
    Activations Density 0.002%

    No Known Activations