© 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. 162931
    Prev
    Next
    INDEX
    Explanations

    whether or thin layer nature

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

    straightforward, easy, and potential

    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
    쿤
    0.49
    createElement
    0.48
    contact
    0.46
    newList
    0.46
    τούν
    0.46
    tudo
    0.45
    pokemon
    0.45
    pictureBox
    0.44
    specific
    0.44
    blog
    0.44
    POSITIVE LOGITS
     ’’
    0.47
    挞
    0.46
     ਕੀ
    0.45
     ਗਈ
    0.45
     mower
    0.44
     “,
    0.44
     طلاب
    0.43
     Isl
    0.43
     hi
    0.43
     adapter
    0.42
    Activations Density 0.000%

    No Known Activations