© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 3231
    Prev
    Next
    INDEX
    Explanations

    select / selecting / selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    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
    附
    0.47
    ્રો
    0.47
     vált
    0.45
    ាតុ
    0.44
    ឹង
    0.44
    完善
    0.42
    <unused1113>
    0.42
    醂
    0.42
     vésicules
    0.41
    ុក
    0.41
    POSITIVE LOGITS
     selection
    1.52
     selecting
    1.51
     Selecting
    1.46
     Selection
    1.44
     selected
    1.38
     selects
    1.38
    选
    1.33
     Selected
    1.32
    選
    1.32
     select
    1.30
    Activations Density 0.008%

    No Known Activations