© 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. 117586
    Prev
    Next
    INDEX
    Explanations

    website links and book titles

    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
     সবই
    -0.06
     affluent
    -0.06
    へ
    -0.06
     افس
    -0.05
    一份
    -0.05
     pasta
    -0.05
    _[
    -0.05
     đều
    -0.05
     ну
    -0.05
    Yo
    -0.05
    POSITIVE LOGITS
    FFECT
    0.06
     at
    0.06
     darkening
    0.06
    Ի
    0.06
    遵循
    0.06
     geeign
    0.06
    inė
    0.06
     Letters
    0.06
     других
    0.06
     weder
    0.06
    Activations Density 0.005%

    No Known Activations