© 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. 189510
    Prev
    Next
    INDEX
    Explanations

    identified before/in

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

    surpassing closed-source models

    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
     sounded
    0.47
     藤
    0.47
    менный
    0.47
    ோ
    0.47
     fascination
    0.46
    dueDate
    0.45
    ုံး
    0.44
     оказалась
    0.44
     phylogenetic
    0.44
    зывает
    0.43
    POSITIVE LOGITS
    </h3>
    0.47
    alis
    0.46
    කු
    0.46
    ades
    0.44
    nies
    0.43
    zani
    0.43
    inis
    0.42
     كنا
    0.42
    uhi
    0.42
     attribut
    0.41
    Activations Density 0.001%

    No Known Activations