© 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. 116887
    Prev
    Next
    INDEX
    Explanations

    ARM Architecture

    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
    theit
    -0.07
     nombr
    -0.07
     вр
    -0.06
     pasti
    -0.06
    ải
    -0.06
     insists
    -0.06
    чені
    -0.06
     roof
    -0.06
     at
    -0.06
     toil
    -0.06
    POSITIVE LOGITS
     AND
    0.06
     and
    0.06
     (!
    0.05
    jub
    0.05
     responded
    0.05
     छोटे
    0.05
     ఉండ
    0.05
    !!!!
    0.05
    浜
    0.05
    Ÿ
    0.05
    Activations Density 0.001%

    No Known Activations