© 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. 226
    Prev
    Next
    INDEX
    Explanations

    species / 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
    ars
    0.27
    infty
    0.26
    sort
    0.26
     HL
    0.26
    celain
    0.26
     வண்ணப்பூச்சு
    0.26
    itate
    0.25
    registered
    0.25
     ହ
    0.25
     lcm
    0.25
    POSITIVE LOGITS
    Hosts
    0.32
    🧾
    0.29
    setType
    0.27
    类型
    0.27
     गोइंग
    0.26
    Niger
    0.26
    SBOM
    0.26
     nField
    0.26
    परि
    0.25
    Ис
    0.25
    Activations Density 0.003%

    No Known Activations