© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130058
    Prev
    Next
    INDEX
    Explanations

    following sentences or descriptions

    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
    Cra
    -0.06
     reject
    -0.06
    usr
    -0.06
    rechts
    -0.06
     tenté
    -0.05
    Փ
    -0.05
     rejecting
    -0.05
     embody
    -0.05
     fickle
    -0.05
    CI
    -0.05
    POSITIVE LOGITS
     easily
    0.07
     توان
    0.07
    我们要
    0.06
     Easily
    0.06
     использоваться
    0.06
     gospodar
    0.06
     विचार
    0.06
     compensated
    0.06
     replacement
    0.06
    ，”
    0.06
    Activations Density 0.003%

    No Known Activations