© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 7813
    Prev
    Next
    INDEX
    Explanations

    skip the

    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
     that
    1.53
     which
    1.50
     and
    1.30
    )
    1.17
    ).
    1.10
     que
    1.05
     i
    1.02
     when
    1.02
     o
    1.00
     their
    0.98
    POSITIVE LOGITS
    ینګ
    1.02
    нибудь
    0.97
    <unused17>
    0.96
    łej
    0.94
     dará
    0.93
     sindical
    0.93
    arán
    0.93
     estará
    0.93
     появится
    0.91
    emplo
    0.91
    Activations Density 3.643%

    No Known Activations