© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87884
    Prev
    Next
    INDEX
    Explanations

    machinery factory and medical specialties

    np_acts-logits-general · gemini-2.5-flash-lite

    legal deduction or commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PrimaryKey
    0.44
     -->
    0.43
    Rite
    0.43
    III
    0.43
     -
    0.42
    ickou
    0.41
    པ
    0.41
     III
    0.41
    ammans
    0.41
    硖
    0.41
    POSITIVE LOGITS
     inoculation
    0.52
     inoculated
    0.52
     itself
    0.49
     vaccinated
    0.46
     unaltered
    0.46
     reacting
    0.46
     ejemplo
    0.45
     negation
    0.45
     exemplo
    0.44
     acreage
    0.44
    Activations Density 0.001%

    No Known Activations