© 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. 120432
    Prev
    Next
    INDEX
    Explanations

    file system 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
     Poetry
    -0.07
     poetry
    -0.07
    評論
    -0.06
     memorabilia
    -0.06
     capitalist
    -0.06
     poet
    -0.06
     pacing
    -0.06
    relevant
    -0.06
     ఇదే
    -0.06
     Builders
    -0.06
    POSITIVE LOGITS
     معظم
    0.07
     பெரும்பாலான
    0.06
     대부분
    0.06
    生地
    0.06
    拠点
    0.06
    授权
    0.06
    私の
    0.06
    कई
    0.06
    शियों
    0.06
     Geography
    0.06
    Activations Density 0.003%

    No Known Activations