© 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. 48878
    Prev
    Next
    INDEX
    Explanations

    possessions and creations

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

    actions occurring repeatedly

    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
    によっては
    0.50
     éste
    0.48
    키
    0.47
     инфраструк
    0.47
    미
    0.46
     효과
    0.46
    positioned
    0.45
    Michelle
    0.45
    Prés
    0.45
    仕
    0.45
    POSITIVE LOGITS
     huvud
    0.45
     telegram
    0.42
     rambling
    0.41
     postcards
    0.41
     отец
    0.40
     membaca
    0.39
    ocycl
    0.39
     cabaret
    0.39
    Примітки
    0.39
     meticulous
    0.39
    Activations Density 0.000%

    No Known Activations