© 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. 131348
    Prev
    Next
    INDEX
    Explanations

    protecting outdoor, near real

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

    steps in a process

    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
    
    0.48
     Mallorca
    0.48
     금
    0.47
     Zeitpunkt
    0.47
     bolstering
    0.47
     Hessen
    0.46
     hedef
    0.46
     목표
    0.46
     ಚುನಾವಣ
    0.46
     ಉಳ
    0.45
    POSITIVE LOGITS
    wot
    0.50
    ainted
    0.49
    ottak
    0.49
    t
    0.48
    The
    0.47
    āv
    0.46
    Tail
    0.46
    ak
    0.46
    :
    0.46
    裤
    0.46
    Activations Density 0.001%

    No Known Activations