© 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. 157031
    Prev
    Next
    INDEX
    Explanations

    phrases of specific word pairs

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

    moves away from / goes beyond

    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
    assignments
    0.50
    ook
    0.47
     बारी
    0.46
    െയി
    0.45
     이라고
    0.44
    ott
    0.43
    啐
    0.43
    າງ
    0.43
    astos
    0.43
     assignments
    0.42
    POSITIVE LOGITS
     כאשר
    0.46
    npmjs
    0.44
     как
    0.43
     לר
    0.43
    Là
    0.43
     עוד
    0.43
     одна
    0.42
     of
    0.42
     fich
    0.42
    Gün
    0.41
    Activations Density 0.002%

    No Known Activations