© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11676
    Prev
    Next
    INDEX
    Explanations

    discussing academic papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ا
    1.48
     postpon
    1.27
    _
    1.25
     gesam
    1.14
     gesamte
    1.11
     Abbreviations
    1.07
     नहीं
    1.05
     Subhanahu
    1.05
    ó
    1.05
    8
    1.04
    POSITIVE LOGITS
    bolos
    1.16
    يد
    1.12
    ד
    1.10
    ства
    1.07
    éléments
    1.07
     дать
    1.04
    сында
    1.01
    ශ්
    1.00
    ુ
    1.00
    न
    0.99
    Activations Density 0.018%

    No Known Activations