© 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. 174627
    Prev
    Next
    INDEX
    Explanations

    mean of statements

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

    categorized lists

    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
    ધાનસભા
    0.42
    arrerol
    0.42
     вернуть
    0.42
     buccal
    0.41
    టర్
    0.40
     добавлен
    0.40
    곁
    0.40
    SDLCheck
    0.40
    шуу
    0.40
    clearRect
    0.40
    POSITIVE LOGITS
     distin
    0.49
    t
    0.47
     con
    0.47
    ۲
    0.46
     CON
    0.46
     Yin
    0.45
     dni
    0.44
    ole
    0.44
     eneste
    0.44
     files
    0.43
    Activations Density 0.000%

    No Known Activations