© 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. 116782
    Prev
    Next
    INDEX
    Explanations

    cave tubing

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

    chemical or medical terms

    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
     supremely
    0.52
     gospel
    0.50
     Daytona
    0.50
    ˢ
    0.48
    ব্র
    0.48
    াঙ্গ
    0.48
    娱
    0.47
    ేశ
    0.47
     DAVIS
    0.46
     Cardinal
    0.46
    POSITIVE LOGITS
    gement
    0.54
    feld
    0.54
    zyma
    0.52
    field
    0.49
    idla
    0.48
    lja
    0.48
    ffield
    0.48
    pping
    0.48
    ngo
    0.47
    farm
    0.47
    Activations Density 0.000%

    No Known Activations