© 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. 129388
    Prev
    Next
    INDEX
    Explanations

    After followed by date/time

    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
     alors
    -0.08
     бонус
    -0.07
     он
    -0.06
     की
    -0.06
    ,
    -0.06
     вами
    -0.06
     like
    -0.06
     entonces
    -0.06
     тогда
    -0.06
     on
    -0.06
    POSITIVE LOGITS
    GBuf
    0.06
     రెండు
    0.06
     राजू
    0.06
    헨
    0.06
     تقوم
    0.06
     dettag
    0.06
     ditu
    0.05
     VHS
    0.05
    Diff
    0.05
     râ
    0.05
    Activations Density 0.002%

    No Known Activations