© 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. 232716
    Prev
    Next
    INDEX
    Explanations

    words followed by other words

    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
    یمو
    0.53
     nelle
    0.51
    भर
    0.49
    <0x8F>
    0.47
    리로
    0.47
    çin
    0.47
    initpos
    0.47
     remon
    0.46
     tempore
    0.46
    here
    0.46
    POSITIVE LOGITS
    撅
    0.53
     Vou
    0.46
     Produkten
    0.46
    鵑
    0.45
    蒾
    0.44
     Shops
    0.44
     Crystallogr
    0.44
    Products
    0.43
     Prothorax
    0.43
     diagonalizable
    0.42
    Activations Density 0.000%

    No Known Activations