© 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. 101648
    Prev
    Next
    INDEX
    Explanations

    bearing units and world

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

    athletically, aircraft, starting, tip

    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
     $>
    0.47
     cassette
    0.47
     journalist
    0.44
     emeritus
    0.44
     JK
    0.44
     alumnus
    0.44
     \#
    0.43
     Novartis
    0.43
     influencer
    0.43
     mediation
    0.43
    POSITIVE LOGITS
     размеров
    0.52
     размера
    0.45
     طریقے
    0.45
    🐷
    0.45
    🍙
    0.45
    に行く
    0.45
    )*((
    0.44
     στον
    0.44
     gobier
    0.44
    भरा
    0.44
    Activations Density 0.001%

    No Known Activations