© 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. 53418
    Prev
    Next
    INDEX
    Explanations

    dates and specific events

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

    remote control settings

    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
     ZONE
    0.47
     scene
    0.45
     aeronaut
    0.45
    屏
    0.45
    ષ
    0.45
     DES
    0.44
     STOR
    0.42
     HOST
    0.42
     রাত্র
    0.42
     monod
    0.41
    POSITIVE LOGITS
     વચ્
    0.49
     þis
    0.48
     угла
    0.46
     опу
    0.46
     samoglas
    0.45
    {*
    0.45
     доходов
    0.44
    تل
    0.44
     سبيل
    0.44
     employé
    0.42
    Activations Density 0.000%

    No Known Activations