© 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. 183811
    Prev
    Next
    INDEX
    Explanations

    weekly diary, judging, Gay?, Tuesday before

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

    illustration idea, gradient vector, rank of words

    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
    牫
    0.49
     ҳа
    0.48
     древ
    0.48
     ಮತ
    0.47
    㡚
    0.47
     вычисли
    0.46
     выс
    0.46
    туа
    0.46
     система
    0.46
     காவல்
    0.46
    POSITIVE LOGITS
    in
    0.64
    y
    0.56
    s
    0.55
    am
    0.53
     Wien
    0.51
     Fruits
    0.50
    S
    0.50
    :
    0.50
     Fruit
    0.49
    Fruit
    0.48
    Activations Density 0.004%

    No Known Activations