© 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. 203653
    Prev
    Next
    INDEX
    Explanations

    device driver

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

    simulate, negative reply, direct

    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
    -*
    0.50
     emigrated
    0.49
    l
    0.49
    son
    0.47
     immigrated
    0.46
    }+{
    0.45
    #-
    0.45
    ([
    0.45
    ('+
    0.44
    {*
    0.44
    POSITIVE LOGITS
     розмі
    0.52
     роз
    0.51
     рыб
    0.50
     Роз
    0.49
     pointillés
    0.47
     grids
    0.45
     lorsque
    0.45
    เพลง
    0.45
    닳
    0.44
     supérieure
    0.44
    Activations Density 0.000%

    No Known Activations