© 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. 212570
    Prev
    Next
    INDEX
    Explanations

    pedaling a bike

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

    HTML structure and content

    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
     تعیین
    0.60
     मैनेज
    0.59
    owneri
    0.59
    它們
    0.53
    ParamNum
    0.52
     тях
    0.52
    實
    0.52
     ನಿರ್
    0.51
     оптими
    0.51
    OfType
    0.50
    POSITIVE LOGITS
     c
    0.57
     Ped
    0.56
     ped
    0.55
    ped
    0.53
    Ped
    0.52
     pictures
    0.52
     a
    0.51
     streets
    0.50
     :
    0.49
     pedals
    0.49
    Activations Density 0.000%

    No Known Activations