© 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. 116318
    Prev
    Next
    INDEX
    Explanations

    A longitudinal

    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
     your
    -0.07
     the
    -0.07
     nhưng
    -0.07
    けど
    -0.07
     যাদের
    -0.07
     pierwsze
    -0.06
     nahezu
    -0.06
     those
    -0.06
     or
    -0.06
     merasakan
    -0.06
    POSITIVE LOGITS
     (
    0.07
     cascading
    0.06
     (&
    0.06
     Gl
    0.05
    ().
    0.05
     Therefore
    0.05
     लिं
    0.05
    GRE
    0.05
     consumes
    0.05
     -
    0.05
    Activations Density 0.003%

    No Known Activations