© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 115946
    Prev
    Next
    INDEX
    Explanations

    "previous" / format

    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
    Negative Logits
     каждого
    -0.06
     jedes
    -0.06
     Representatives
    -0.05
     each
    -0.05
    ");
    -0.05
    Representatives
    -0.05
    ipple
    -0.05
     mỗi
    -0.05
    edes
    -0.05
     ለእ
    -0.05
    POSITIVE LOGITS
     previous
    0.07
     nuestros
    0.07
     condense
    0.07
     thánh
    0.07
     penchant
    0.07
     our
    0.06
     nuest
    0.06
    以前
    0.06
     Tuesday
    0.06
     poprzed
    0.06
    Activations Density 0.002%

    No Known Activations