© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111135
    Prev
    Next
    INDEX
    Explanations

    your child

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

    damage to intestinal wall

    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
     conditioners
    0.52
    ພວກເຮົາ
    0.48
     utilisent
    0.47
     spasms
    0.46
    赂
    0.46
     exacerbate
    0.45
     Particles
    0.45
     Veranst
    0.45
    újt
    0.45
     aspire
    0.44
    POSITIVE LOGITS
    omar
    0.46
    Serializable
    0.45
    annotate
    0.44
    again
    0.43
    </th>
    0.43
    ASC
    0.42
     tehdä
    0.42
     л
    0.42
     بودن
    0.42
    SE
    0.41
    Activations Density 0.001%

    No Known Activations