© 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. 72814
    Prev
    Next
    INDEX
    Explanations

    ear studs

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

    potential reversal

    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
     économique
    0.44
     मिरर
    0.44
     spécifique
    0.44
     एडिटिंग
    0.44
    ში
    0.44
     آئینے
    0.44
    𝗩
    0.43
    Dimension
    0.43
     mirroring
    0.43
    評價
    0.43
    POSITIVE LOGITS
     Birthday
    0.44
     Brook
    0.43
     zatem
    0.43
    osta
    0.42
    <0x80>
    0.41
     হোস্ট
    0.41
     ISNI
    0.39
     বন
    0.39
     Jharkhand
    0.39
     PhoneNumber
    0.39
    Activations Density 0.001%

    No Known Activations