© 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. 136461
    Prev
    Next
    INDEX
    Explanations

    list delimiters

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

    reducing bias

    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
     महासभा
    0.52
    坵
    0.52
     तापमान
    0.47
     स्पर्श
    0.47
    未能
    0.46
     machte
    0.46
    Smoothing
    0.44
     नाराजगी
    0.44
    ऊंगी
    0.44
     sabemos
    0.43
    POSITIVE LOGITS
     in
    0.54
    ও
    0.48
     scenic
    0.47
    l
    0.47
    W
    0.46
     arctic
    0.46
    N
    0.45
    <0x80>
    0.45
     speeds
    0.45
     from
    0.45
    Activations Density 0.000%

    No Known Activations