© 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. 68410
    Prev
    Next
    INDEX
    Explanations

    zip codes

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

    addresses

    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
    ay
    0.54
    by
    0.49
     "
    0.49
    0.49
    in
    0.47
    y
    0.46
    is
    0.46
    ‘
    0.46
    L
    0.45
    <em>
    0.45
    POSITIVE LOGITS
     nisid
    0.50
     sajana
    0.48
     Antrag
    0.48
     polysaccharide
    0.47
    ផ្គ
    0.46
     తాగ
    0.46
     variar
    0.45
     jaga
    0.45
     ሂደ
    0.45
     توانند
    0.45
    Activations Density 0.006%

    No Known Activations