© 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. 129433
    Prev
    Next
    INDEX
    Explanations

    CF and KO mice

    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
    rases
    -0.07
     desaparecer
    -0.06
     dificuldade
    -0.06
     efforts
    -0.06
     मतदारसंघात
    -0.06
    difficult
    -0.06
     सर्व
    -0.06
     uygul
    -0.06
     conceptions
    -0.06
    orneys
    -0.06
    POSITIVE LOGITS
     idling
    0.06
     الحكومة
    0.06
     templates
    0.05
     accommodates
    0.05
    政府
    0.05
     inherently
    0.05
     Italy
    0.05
    textures
    0.05
     jähr
    0.05
     actualidad
    0.05
    Activations Density 0.037%

    No Known Activations