© 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. 130884
    Prev
    Next
    INDEX
    Explanations

    role of

    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
     Command
    -0.06
     (!
    -0.06
     BAR
    -0.06
     brasile
    -0.06
     मनी
    -0.05
     science
    -0.05
     জানিতে
    -0.05
    ango
    -0.05
    但我
    -0.05
     Cred
    -0.05
    POSITIVE LOGITS
     which
    0.07
     would
    0.07
     has
    0.06
     पुन्हा
    0.06
    éndose
    0.06
     które
    0.06
     avrebbe
    0.06
     oddly
    0.06
    шина
    0.06
     って
    0.06
    Activations Density 0.046%

    No Known Activations