© 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. 240499
    Prev
    Next
    INDEX
    Explanations

    phrases after articles or descriptors

    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
    ধর্
    0.50
    า
    0.49
    Ꮞ
    0.48
    （
    0.46
     entram
    0.45
    ή
    0.44
     copywriting
    0.44
     remedied
    0.44
    ุก
    0.44
     ($(
    0.44
    POSITIVE LOGITS
    Atom
    0.60
     Atom
    0.55
     زده
    0.50
     ź
    0.47
    स्था
    0.46
     тер
    0.46
    Cc
    0.46
    ATOM
    0.46
    飕
    0.46
    nek
    0.46
    Activations Density 0.000%

    No Known Activations