© 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. 120158
    Prev
    Next
    INDEX
    Explanations

    suggestions for improvements

    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
     excuses
    -0.06
     if
    -0.06
     =
    -0.06
     Falle
    -0.06
    csname
    -0.06
     이에
    -0.06
     correspondingly
    -0.06
     যথা
    -0.06
     해당하는
    -0.05
     গো
    -0.05
    POSITIVE LOGITS
     আরও
    0.09
    future
    0.08
     future
    0.07
    Ttest
    0.07
     huge
    0.07
     erity
    0.06
     upay
    0.06
     adesso
    0.06
     além
    0.06
     more
    0.06
    Activations Density 0.014%

    No Known Activations