© 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. 10386
    Prev
    Next
    INDEX
    Explanations

    go/car/fast until/in

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

    data, Changes, flow, store, inactivity, exposed

    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
    არა
    0.30
    larının
    0.30
    ดี๋ยว
    0.29
    라
    0.29
    당
    0.28
    력
    0.28
    לי
    0.27
    꿍
    0.27
    ლებ
    0.27
    گران
    0.27
    POSITIVE LOGITS
     ત્યારે
    0.29
     ASAP
    0.29
     inmedi
    0.28
     yanında
    0.27
     acompañada
    0.26
     Sx
    0.26
     accompanied
    0.26
     WITH
    0.25
     ಘೋಷ
    0.25
     +.
    0.25
    Activations Density 0.090%

    No Known Activations