© 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. 186121
    Prev
    Next
    INDEX
    Explanations

    fun, exciting, talent, life, help

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

    before, sometimes, even

    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
    connector
    0.50
    ურთი
    0.49
    တွင်
    0.47
    cił
    0.47
    ُونَ
    0.47
     conveyance
    0.46
    either
    0.46
    े
    0.46
     connector
    0.45
     discreet
    0.45
    POSITIVE LOGITS
     étrangers
    0.49
     여섯
    0.47
     tasse
    0.46
     الناس
    0.46
     والش
    0.46
    生活的
    0.46
     sechs
    0.45
     עצ
    0.45
    ما
    0.45
    re
    0.44
    Activations Density 0.000%

    No Known Activations