© 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. 117092
    Prev
    Next
    INDEX
    Explanations

    type suffix or prefix

    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
     on
    -0.08
     for
    -0.08
     आध्यात्म
    -0.07
     as
    -0.07
     or
    -0.07
     také
    -0.06
     på
    -0.06
     थरूर
    -0.06
     at
    -0.06
     на
    -0.06
    POSITIVE LOGITS
    jp
    0.06
    who
    0.06
     indiscriminate
    0.06
     who
    0.06
     অধিকাংশ
    0.05
    new
    0.05
    ir
    0.05
     බො
    0.05
    must
    0.05
    ziej
    0.05
    Activations Density 0.001%

    No Known Activations