© 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. 119935
    Prev
    Next
    INDEX
    Explanations

    build state

    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
    BANG
    -0.07
    क्तिक
    -0.06
     potrebno
    -0.06
     dodat
    -0.06
    retail
    -0.06
     adicionales
    -0.05
    ச்செ
    -0.05
    additional
    -0.05
     underlies
    -0.05
     Franck
    -0.05
    POSITIVE LOGITS
    别人
    0.06
     initiative
    0.06
     new
    0.06
     Verification
    0.06
     Verify
    0.06
     Verifica
    0.06
    Verifier
    0.06
     стали
    0.06
    可以通过
    0.06
     sabia
    0.06
    Activations Density 0.061%

    No Known Activations