© 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. 117920
    Prev
    Next
    INDEX
    Explanations

    infinity, large, variables, one, differential, new

    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
     unwillingness
    -0.07
     אחד
    -0.07
    must
    -0.07
     خلاف
    -0.06
     glycolysis
    -0.06
     tensions
    -0.06
    最后一个
    -0.06
     कठिना
    -0.06
     must
    -0.06
    واي
    -0.06
    POSITIVE LOGITS
     చో
    0.06
     charakter
    0.06
     without
    0.06
     بدون
    0.06
     oblong
    0.06
     équipée
    0.05
     ancillary
    0.05
     कू
    0.05
     Other
    0.05
     large
    0.05
    Activations Density 0.004%

    No Known Activations