© 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. 88732
    Prev
    Next
    INDEX
    Explanations

    extended genealogy, page numbers, sophisticated

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

    specific entities and topics

    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
     فريق
    0.48
     magasiner
    0.48
    YER
    0.47
     squadre
    0.47
     sauve
    0.47
    泬
    0.47
    鐟
    0.47
     אתה
    0.46
     véh
    0.44
     جاي
    0.43
    POSITIVE LOGITS
    ipedia
    0.53
     colourful
    0.51
     colorful
    0.48
    یشنل
    0.47
     comparability
    0.47
    家
    0.46
    ایی
    0.45
    s
    0.45
    齧
    0.45
     Costs
    0.45
    Activations Density 0.000%

    No Known Activations