© 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. 18239
    Prev
    Next
    INDEX
    Explanations

    mini-game, dust, faith, Elizabeth

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

    it makes humans and gamers

    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
     или
    0.58
     ឬ
    0.49
     혹은
    0.46
     prolet
    0.46
    或是
    0.45
     அல்லது
    0.45
    in
    0.44
     и
    0.43
     หรือ
    0.43
    了
    0.43
    POSITIVE LOGITS
     empêcher
    0.50
     fortiter
    0.48
     respiratoires
    0.48
     pravidel
    0.45
     vaisse
    0.44
    ucks
    0.44
     timeouts
    0.44
     washes
    0.43
     gamer
    0.43
     estabelecimento
    0.43
    Activations Density 0.000%

    No Known Activations