© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118798
    Prev
    Next
    INDEX
    Explanations

    LARC, In Vitro, St Vigeans, Aralen, Blue Corner, Landauer, Enthusiasm, Shabby Chic, Courtesans, Benign

    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
     pochod
    -0.05
     MPS
    -0.05
     CMB
    -0.05
    نة
    -0.05
    会有
    -0.05
    ane
    -0.05
     ingen
    -0.05
    ക്ഷ
    -0.05
     comprehensive
    -0.05
    ном
    -0.05
    POSITIVE LOGITS
    TWO
    0.08
    ２
    0.07
     Spaniards
    0.07
     TWO
    0.07
     भीतर
    0.07
     ఇటీవల
    0.06
    ８
    0.06
    Existe
    0.06
    ܘ
    0.06
    izlik
    0.06
    Activations Density 0.040%

    No Known Activations