© 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. 120702
    Prev
    Next
    INDEX
    Explanations

    Canon EF

    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
     resolute
    -0.07
     by
    -0.07
     excepto
    -0.07
     mindestens
    -0.07
    tournament
    -0.07
     þe
    -0.07
     except
    -0.06
     kecuali
    -0.06
     ench
    -0.06
     peaks
    -0.06
    POSITIVE LOGITS
    ,
    0.06
     (
    0.06
    চালক
    0.06
     nostra
    0.05
     sua
    0.05
     recours
    0.05
    Doesn
    0.05
    ，
    0.05
     limitations
    0.05
    there
    0.05
    Activations Density 0.002%

    No Known Activations