© 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. 48368
    Prev
    Next
    INDEX
    Explanations

    deals like Groupon

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

    date marks beginning of invasion

    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
    办法
    0.46
    torrent
    0.44
    cwnd
    0.43
     ٹیم
    0.43
     ٹ
    0.43
    超越
    0.42
    航班
    0.42
    队
    0.42
     অব্যাহতি
    0.42
    )}$,
    0.41
    POSITIVE LOGITS
     at
    0.55
     to
    0.49
     was
    0.48
     indicates
    0.48
     nä
    0.47
     decrease
    0.46
     în
    0.46
     addition
    0.46
     number
    0.46
     favorable
    0.45
    Activations Density 0.000%

    No Known Activations