© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 122259
    Prev
    Next
    INDEX
    Explanations

    relative low

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

    days to reach

    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
     کھانے
    0.50
     কন্যার
    0.46
     کھانا
    0.46
    溲
    0.45
     কন্যা
    0.44
     لے
    0.43
    ဖြင့်
    0.43
    stateMutability
    0.43
     കൊണ്ട്
    0.43
    গামী
    0.42
    POSITIVE LOGITS
    H
    0.57
    O
    0.55
    \
    0.55
    K
    0.53
     s
    0.52
     j
    0.52
     evident
    0.51
     pape
    0.49
    R
    0.49
    ana
    0.48
    Activations Density 0.000%

    No Known Activations