© 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. 119947
    Prev
    Next
    INDEX
    Explanations

    code generator, version, if you, question, here we

    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
    として
    -0.07
    探索
    -0.07
     makhluk
    -0.06
     стрем
    -0.06
    徘
    -0.06
     loosely
    -0.06
     continuare
    -0.06
     Ancak
    -0.06
    unfinished
    -0.06
    谈
    -0.06
    POSITIVE LOGITS
     including
    0.08
    including
    0.07
     incluyendo
    0.07
     INCLUDING
    0.06
    generated
    0.06
     COLOR
    0.06
    covered
    0.06
     माझ्या
    0.06
     خواهند
    0.06
     crushed
    0.06
    Activations Density 0.014%

    No Known Activations