© 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. 120254
    Prev
    Next
    INDEX
    Explanations

    English pamphleteer

    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
    copter
    -0.06
    更快
    -0.06
     लवकर
    -0.06
     ಪಕ್ಷ
    -0.06
    家の
    -0.06
     various
    -0.06
     cikin
    -0.06
     பாராட்ட
    -0.06
     خلال
    -0.06
     পারে
    -0.05
    POSITIVE LOGITS
    🧐
    0.07
     railway
    0.07
    靠
    0.06
     embankment
    0.06
     intends
    0.06
     interprets
    0.06
    🎬
    0.06
     earns
    0.06
     satu
    0.06
     fotografia
    0.06
    Activations Density 0.008%

    No Known Activations