© 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. 238424
    Prev
    Next
    INDEX
    Explanations

    news and articles

    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
    лектрон
    0.54
     elettron
    0.52
    nag
    0.47
     Middleton
    0.45
    la
    0.44
    DOUT
    0.43
    랜
    0.43
     fratt
    0.43
     assegn
    0.43
    電子
    0.42
    POSITIVE LOGITS
    ᱓
    0.52
    initiative
    0.50
    figuration
    0.49
    country
    0.48
     initiative
    0.48
     بسیاری
    0.47
    ells
    0.47
    financing
    0.46
    の両
    0.46
    भेद
    0.46
    Activations Density 0.000%

    No Known Activations