© 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. 128750
    Prev
    Next
    INDEX
    Explanations

    permission denied or unauthorized access

    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
     they
    -0.10
     только
    -0.07
     only
    -0.07
    cra
    -0.07
     mereka
    -0.07
     فقط
    -0.07
     everyone
    -0.07
     ONLY
    -0.07
    They
    -0.07
     Только
    -0.07
    POSITIVE LOGITS
     kone
    0.06
     최종
    0.05
     bals
    0.05
     SPOT
    0.05
     vividly
    0.05
     वगैर
    0.05
     আপন
    0.05
     secreto
    0.05
     final
    0.05
     очередной
    0.05
    Activations Density 0.009%

    No Known Activations