© 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. 117260
    Prev
    Next
    INDEX
    Explanations

    version numbers and package management

    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
     entrare
    -0.06
     caracteriza
    -0.06
     growth
    -0.06
    Anime
    -0.06
     আর্ম
    -0.06
     cultivars
    -0.06
     तसेच
    -0.06
    車種
    -0.06
     anime
    -0.06
    odore
    -0.06
    POSITIVE LOGITS
     your
    0.07
     제공
    0.06
    inden
    0.06
     आपका
    0.06
     NONE
    0.06
    your
    0.06
     preval
    0.06
     অস্থ
    0.06
    instead
    0.06
     resourceful
    0.06
    Activations Density 0.008%

    No Known Activations