© 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. 116778
    Prev
    Next
    INDEX
    Explanations

    place 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
     dando
    -0.07
    จะ
    -0.07
     ګرځنده
    -0.06
     بیاکت
    -0.06
     siendo
    -0.06
     откуда
    -0.06
     predicting
    -0.06
     নাম
    -0.06
     última
    -0.06
    現在は
    -0.06
    POSITIVE LOGITS
    就可以了
    0.07
    কেও
    0.07
     を
    0.07
     also
    0.06
     Until
    0.06
     already
    0.06
     Also
    0.06
     মধ্যেও
    0.06
     implications
    0.06
     ইউনিট
    0.06
    Activations Density 0.040%

    No Known Activations