© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40254
    Prev
    Next
    INDEX
    Explanations

    digits following symbols or in sequences

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

    contrasting traditional methods

    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
    aggregated
    0.46
    ulations
    0.46
    relations
    0.46
    및
    0.45
    omens
    0.45
    rightsquigarrow
    0.45
    rim
    0.44
    usuarios
    0.44
    푎
    0.44
    themem
    0.43
    POSITIVE LOGITS
     enfim
    0.52
     dos
    0.50
     convertirse
    0.49
     blive
    0.48
     Los
    0.47
     deno
    0.47
     santi
    0.47
     incul
    0.46
     ibn
    0.46
     become
    0.46
    Activations Density 0.000%

    No Known Activations