© 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. 117662
    Prev
    Next
    INDEX
    Explanations

    numbers and orders

    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
     siker
    -0.07
     shortcoming
    -0.06
    所有
    -0.06
     &
    -0.06
     Default
    -0.05
     Bison
    -0.05
     bernama
    -0.05
     பாரம்பரிய
    -0.05
     любые
    -0.05
    khart
    -0.05
    POSITIVE LOGITS
    యన
    0.07
     öğretmen
    0.06
     തൊ
    0.06
     }},
    0.06
     стомато
    0.06
     transm
    0.06
     સાં
    0.06
     greatest
    0.06
     PICTOGRAM
    0.06
    İY
    0.06
    Activations Density 0.016%

    No Known Activations