© 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. 116950
    Prev
    Next
    INDEX
    Explanations

    failure to control leads to pseudo

    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
     предстоя
    -0.07
    किम
    -0.06
     Kanton
    -0.06
     절대
    -0.06
     hafif
    -0.06
     negocio
    -0.06
    仅仅
    -0.06
    ష్టం
    -0.06
     Bedürfnisse
    -0.05
     proposte
    -0.05
    POSITIVE LOGITS
     asks
    0.06
     oste
    0.06
     autént
    0.06
    యిత
    0.06
     thus
    0.06
    generate
    0.06
     oike
    0.06
    Asked
    0.06
     actives
    0.06
     generate
    0.06
    Activations Density 0.043%

    No Known Activations