© 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. 210794
    Prev
    Next
    INDEX
    Explanations

    story alone or Philosophy

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

    body composition measurement

    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
     luminosity
    0.46
     productName
    0.45
    ഉ
    0.42
     součástí
    0.41
     activation
    0.41
     conformations
    0.41
     добавить
    0.40
    悽
    0.40
     aggiungere
    0.40
    poco
    0.39
    POSITIVE LOGITS
    itada
    0.48
    ieros
    0.45
    গল
    0.45
    いで
    0.45
    ecake
    0.44
     Munro
    0.43
    aginaw
    0.43
     etern
    0.43
     Maitland
    0.43
    iunea
    0.42
    Activations Density 0.001%

    No Known Activations