© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 33039
    Prev
    Next
    INDEX
    Explanations

    home and cleanliness, color and spectrum, doctor names

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

    "fmt." prefix in go code

    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
     padrão
    0.46
     Fortress
    0.45
    "
    0.45
    †
    0.45
     Farr
    0.44
    ·
    0.44
     Sir
    0.43
     Sall
    0.43
     Reprint
    0.43
     Nunn
    0.43
    POSITIVE LOGITS
    ekeeping
    0.53
    先日
    0.51
    ёт
    0.50
    ολ
    0.49
    пропетров
    0.49
    рения
    0.48
    ственной
    0.48
    ለያ
    0.48
    㜖
    0.48
    াহরণ
    0.47
    Activations Density 0.001%

    No Known Activations