© 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. 40-GEMMASCOPE-2-RES-262K
    7. 194155
    Prev
    Next
    INDEX
    Explanations

    conditional selection with "where"

    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/layer_40_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
     événement
    0.39
     αυτο
    0.39
    啝
    0.39
    лефон
    0.38
     Segunda
    0.38
     الاخ
    0.38
     Outside
    0.38
    ហ
    0.37
    оны
    0.37
     vilken
    0.37
    POSITIVE LOGITS
     seamless
    0.44
     tibia
    0.40
    bie
    0.40
    ATTER
    0.39
    ARTI
    0.38
    izable
    0.38
    ER
    0.37
     painless
    0.37
     spoken
    0.36
     zoning
    0.36
    Activations Density 0.000%

    No Known Activations