© 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. 120135
    Prev
    Next
    INDEX
    Explanations

    and + names

    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
     mantener
    -0.07
    সমস্ত
    -0.07
     dreadful
    -0.07
     hapless
    -0.06
     cleverly
    -0.06
     веду
    -0.06
     जरा
    -0.06
     dynamically
    -0.06
     supremely
    -0.06
     definitivamente
    -0.06
    POSITIVE LOGITS
    㕩
    0.06
    㛣
    0.06
    ार्ड
    0.06
     sought
    0.06
     amico
    0.06
    ார்
    0.06
    arelli
    0.05
     பிறந்த
    0.05
     जानकार
    0.05
    :
    0.05
    Activations Density 0.002%

    No Known Activations