© 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. 31-GEMMASCOPE-2-RES-262K
    7. 40957
    Prev
    Next
    INDEX
    Explanations

    global reserves, platforms, natures, pitch, cannabin

    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_31_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
    MA
    0.44
    L
    0.43
    由
    0.43
    ट
    0.42
    package
    0.42
    ха
    0.42
    ֨
    0.42
    ME
    0.42
    ট
    0.41
    на
    0.41
    POSITIVE LOGITS
     idiots
    0.55
     liste
    0.54
     hobbies
    0.50
     discipline
    0.49
    rafi
    0.49
     comportamenti
    0.49
     pathways
    0.49
     costa
    0.47
     roadmap
    0.47
     refinement
    0.47
    Activations Density 0.000%

    No Known Activations