© 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. 3554
    Prev
    Next
    INDEX
    Explanations

    objects being held

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

    objects and containers

    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
    ब
    0.30
     संख्या
    0.28
    
    0.27
     کاهش
    0.27
    ทีม
    0.27
    σ
    0.26
     அதாவது
    0.26
    พวก
    0.26
    $[
    0.26
     মানুষ
    0.25
    POSITIVE LOGITS
     holder
    0.43
     held
    0.33
     puesta
    0.31
    holder
    0.31
     Holders
    0.31
     pouch
    0.31
     dangling
    0.31
     flung
    0.30
     Holder
    0.30
     keychain
    0.29
    Activations Density 0.433%

    No Known Activations