© 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. 206658
    Prev
    Next
    INDEX
    Explanations

    elected official, served purpose

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

    Word documents; alignment

    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
     comic
    0.49
     eig
    0.45
     sveik
    0.45
     media
    0.45
    d
    0.44
     distinct
    0.43
    ровень
    0.43
     half
    0.43
    ায়ণ
    0.43
     reactance
    0.42
    POSITIVE LOGITS
    नंतर
    0.52
    不再
    0.46
    цій
    0.45
    Chicken
    0.43
    eram
    0.43
    裂
    0.43
    充满了
    0.42
    人民币
    0.42
    iros
    0.42
    充满
    0.42
    Activations Density 0.001%

    No Known Activations