© 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. 122258
    Prev
    Next
    INDEX
    Explanations

    get a, record master, latest YA

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

    dictate your moves

    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
     convuls
    0.48
     Otis
    0.46
     hưởng
    0.46
     CONTIN
    0.45
    \}=
    0.44
    蛆
    0.44
     பாதிக்கப்பட்ட
    0.43
    发放
    0.42
    ुस्तान
    0.42
     Jahan
    0.42
    POSITIVE LOGITS
    채
    0.49
    рд
    0.46
    мов
    0.46
     incorporates
    0.46
    ৌম
    0.45
     mieux
    0.45
    Fonts
    0.45
    は
    0.45
    Skeleton
    0.44
    Endereco
    0.44
    Activations Density 0.000%

    No Known Activations