© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129664
    Prev
    Next
    INDEX
    Explanations

    spatial directions and extents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    if
    -0.07
    j
    -0.06
    pp
    -0.06
     If
    -0.06
    st
    -0.06
    sw
    -0.06
    ap
    -0.05
     if
    -0.05
     May
    -0.05
    sp
    -0.05
    POSITIVE LOGITS
     extrapol
    0.07
    具体的な
    0.06
    Rural
    0.06
    TimeDict
    0.06
     queste
    0.06
    InfoPlistPath
    0.06
     transportar
    0.06
    𒌋
    0.06
     Shazam
    0.06
     demons
    0.06
    Activations Density 0.002%

    No Known Activations