© 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. 165962
    Prev
    Next
    INDEX
    Explanations

    religious and poor

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

    paleontological, engineers, agricult

    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
    listen
    0.48
    trying
    0.45
    fix
    0.44
    ษฐ
    0.44
     rối
    0.44
    anchez
    0.43
    ت
    0.43
    ten
    0.42
     ডিস
    0.42
     listen
    0.42
    POSITIVE LOGITS
     infrastrukt
    0.48
    ָ
    0.44
     agricult
    0.44
    ๚
    0.44
     infrastructures
    0.43
    物品
    0.42
     Faun
    0.42
    ְ
    0.41
     Larg
    0.41
     Agricult
    0.40
    Activations Density 0.001%

    No Known Activations