© 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. 145498
    Prev
    Next
    INDEX
    Explanations

    saving cash

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

    NATS

    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
    Prince
    0.54
    λού
    0.53
    Ս
    0.50
    England
    0.50
    рта
    0.49
    Teddy
    0.48
    が通販
    0.48
    رخ
    0.48
    Prairie
    0.48
    Sciences
    0.47
    POSITIVE LOGITS
     interferes
    0.55
    k
    0.55
    ,[
    0.52
     Stry
    0.51
     Eren
    0.51
     Exxon
    0.50
     Kom
    0.50
    的方向
    0.49
     Isis
    0.49
     Odysseus
    0.49
    Activations Density 0.000%

    No Known Activations