© 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. 137474
    Prev
    Next
    INDEX
    Explanations

    a specific category

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

    traditional vs new

    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
     Virginia
    0.49
     County
    0.47
    ս
    0.45
     Minnesota
    0.44
    Virginia
    0.44
     lecture
    0.43
     Portland
    0.43
     family
    0.42
    éch
    0.42
     accl
    0.42
    POSITIVE LOGITS
     γλώ
    0.56
    вался
    0.48
    钅
    0.48
     explodes
    0.46
     lLoginID
    0.45
    欲
    0.45
     জা
    0.45
     জটিল
    0.45
     अत
    0.45
    tpVar
    0.45
    Activations Density 0.001%

    No Known Activations