© 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. 116702
    Prev
    Next
    INDEX
    Explanations

    story or situation description

    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
     پلان
    -0.06
     ביותר
    -0.06
     soweit
    -0.06
    orderDisplay
    -0.06
     Shia
    -0.06
    myst
    -0.06
    ⵍ
    -0.05
    requirement
    -0.05
    얘
    -0.05
    (!
    -0.05
    POSITIVE LOGITS
     a
    0.06
     how
    0.06
     tym
    0.06
     the
    0.06
     powering
    0.06
     первым
    0.06
     первом
    0.06
     was
    0.06
     first
    0.06
     various
    0.06
    Activations Density 0.016%

    No Known Activations