© 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. 117082
    Prev
    Next
    INDEX
    Explanations

    topic of the day

    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
    ;.
    -0.07
     إذا
    -0.06
    ;
    -0.06
    ;,
    -0.06
    ”;
    -0.06
    ;#
    -0.06
    they
    -0.05
    ’;
    -0.05
     aspects
    -0.05
     attributes
    -0.05
    POSITIVE LOGITS
     remarkable
    0.07
     remarquable
    0.07
    市场上
    0.07
     hoga
    0.07
     will
    0.06
     некоторые
    0.06
     certains
    0.06
    rafl
    0.06
     полностью
    0.06
     નક્
    0.06
    Activations Density 0.007%

    No Known Activations