© 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. 120388
    Prev
    Next
    INDEX
    Explanations

    Autoloader, Record, key, ECT, Candidates

    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
     purse
    -0.06
    general
    -0.06
    april
    -0.06
    nobody
    -0.06
    generic
    -0.06
     charcoal
    -0.05
     Charcoal
    -0.05
     april
    -0.05
     April
    -0.05
    completely
    -0.05
    POSITIVE LOGITS
    ሐ
    0.07
     Bueno
    0.06
    ică
    0.06
    ценка
    0.06
     размеров
    0.06
    ibald
    0.06
    链路
    0.06
    atsi
    0.06
     الحصول
    0.06
     estadounidenses
    0.06
    Activations Density 0.002%

    No Known Activations