© 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
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241595
    Prev
    Next
    INDEX
    Explanations

    specific entities or measurements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
     affective
    0.63
     disagreeable
    0.56
    huile
    0.56
    piele
    0.55
    धव
    0.54
     FIGURES
    0.54
     doulou
    0.54
    ｭ
    0.52
    <0x8D>
    0.51
     Reiter
    0.51
    POSITIVE LOGITS
    Timestamp
    0.53
    Decrement
    0.52
     localhost
    0.52
     Suddenly
    0.51
     round
    0.51
     Slowly
    0.51
     میچ
    0.50
     Round
    0.50
     langsam
    0.50
     cáo
    0.49
    Activations Density 0.000%

    No Known Activations