© 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. 194738
    Prev
    Next
    INDEX
    Explanations

    specific nouns and their continuations

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

    why they don't work

    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
    д
    0.55
    น
    0.50
    ין
    0.50
    Khal
    0.49
    Investigations
    0.49
    u
    0.49
    Bowling
    0.49
    р
    0.48
    וא
    0.48
    ദ
    0.47
    POSITIVE LOGITS
     Jaaye
    0.52
     magas
    0.49
     talleres
    0.49
    kker
    0.49
     undercover
    0.48
     मटे
    0.48
    chnitten
    0.48
    ifting
    0.47
    anced
    0.47
     dyr
    0.46
    Activations Density 0.000%

    No Known Activations