© 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. 188253
    Prev
    Next
    INDEX
    Explanations

    art, restart, apply, cheap, up

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

    understanding, failing

    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
    i
    0.58
     usc
    0.57
     Promise
    0.50
     Supporting
    0.48
     PTS
    0.48
     stop
    0.47
     broken
    0.46
    broken
    0.46
     Broken
    0.46
    hur
    0.45
    POSITIVE LOGITS
     キー
    0.63
    ව
    0.55
    侏
    0.51
    あなた
    0.50
    KeyCode
    0.50
    順番
    0.50
    តា
    0.49
    AVLNode
    0.49
    nashvillehousing
    0.48
    ที
    0.48
    Activations Density 0.000%

    No Known Activations