© 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. 249102
    Prev
    Next
    INDEX
    Explanations

    continue plans and equip

    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
            
    0.61
     or
    0.59
     clipping
    0.57
     :
    0.53
     {
    0.52
     (
    0.52
     magnifying
    0.52
     갔
    0.52
     ,
    0.51
     is
    0.51
    POSITIVE LOGITS
    ᴅ
    0.54
    техни
    0.52
    исто
    0.51
    致力于
    0.49
    検討
    0.48
    нено
    0.48
    醸
    0.48
    Bitte
    0.47
    Technische
    0.47
    StatusCode
    0.47
    Activations Density 0.001%

    No Known Activations