© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130019
    Prev
    Next
    INDEX
    Explanations

    old followed by certain nouns

    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
     historischen
    -0.07
     पछ
    -0.06
     ослож
    -0.06
     சமீப
    -0.06
     century
    -0.06
     оригі
    -0.06
     bituminous
    -0.06
     vários
    -0.06
     시대
    -0.06
     pestaña
    -0.06
    POSITIVE LOGITS
    :
    0.08
    แก่
    0.06
     हवे
    0.06
     clusters
    0.06
    chid
    0.05
    mean
    0.05
     Karin
    0.05
    ️
    0.05
    راف
    0.05
     মুহুর
    0.05
    Activations Density 0.018%

    No Known Activations