© 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. 128404
    Prev
    Next
    INDEX
    Explanations

    numbers and zeros

    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
    multi
    -0.06
     अपन
    -0.06
    वर्तमान
    -0.06
    стная
    -0.06
     خپل
    -0.06
    Until
    -0.06
     हमरे
    -0.06
     Until
    -0.06
     Com
    -0.05
     Capture
    -0.05
    POSITIVE LOGITS
     not
    0.06
     icy
    0.06
     by
    0.06
    elles
    0.06
     gleich
    0.06
     egypt
    0.06
     theoret
    0.06
     බොහෝ
    0.06
     شاید
    0.06
     لب
    0.05
    Activations Density 0.001%

    No Known Activations