© 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. 117018
    Prev
    Next
    INDEX
    Explanations

    html tag `<`

    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
     behold
    -0.06
    pped
    -0.06
    amazing
    -0.06
     Behold
    -0.06
     amazing
    -0.06
     vraiment
    -0.06
    Pp
    -0.06
     BOTH
    -0.06
     itself
    -0.06
     ತನ್ನ
    -0.06
    POSITIVE LOGITS
    由此
    0.06
     así
    0.06
     genauso
    0.06
    ψ
    0.06
     पहली
    0.06
     Anders
    0.06
     nonché
    0.06
     सब
    0.05
     čty
    0.05
     अनुशंसा
    0.05
    Activations Density 0.010%

    No Known Activations