© 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. 128426
    Prev
    Next
    INDEX
    Explanations

    connection closed or reset

    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
     giveaway
    -0.06
     Giveaway
    -0.06
     not
    -0.06
    GetCurrent
    -0.06
     capítulo
    -0.06
     (’
    -0.06
     مذکور
    -0.06
     Rock
    -0.05
     riduzione
    -0.05
     ROCK
    -0.05
    POSITIVE LOGITS
     after
    0.07
     после
    0.06
     आफ्टर
    0.06
     integr
    0.06
    ौला
    0.06
    磋商
    0.06
     dopo
    0.06
     দর্শন
    0.06
    correspond
    0.06
     після
    0.06
    Activations Density 0.005%

    No Known Activations