© 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. 83823
    Prev
    Next
    INDEX
    Explanations

    after your order

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

    spatial concepts and actions

    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
     తిన
    0.47
    РА
    0.46
    Η
    0.46
     कैद
    0.45
    Ν
    0.45
    ตู
    0.44
    เว็บ
    0.44
    Ка
    0.43
    MIC
    0.43
    5
    0.43
    POSITIVE LOGITS
     the
    0.54
     anaemia
    0.52
     diad
    0.52
     cards
    0.52
     pouring
    0.50
     sizing
    0.50
     diab
    0.49
     saith
    0.48
     our
    0.48
     erster
    0.48
    Activations Density 0.002%

    No Known Activations