© 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. 118389
    Prev
    Next
    INDEX
    Explanations

    special characters and links

    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
     पहिला
    -0.07
     first
    -0.06
     første
    -0.06
     लेके
    -0.05
     uses
    -0.05
    ij
    -0.05
    first
    -0.05
     personnels
    -0.05
    ll
    -0.05
    ôté
    -0.05
    POSITIVE LOGITS
     you
    0.08
     вам
    0.08
     benötigt
    0.07
     necessária
    0.07
     potrzeb
    0.07
    ..!
    0.07
     ?!
    0.07
     필요한
    0.07
     आपको
    0.07
     (!)
    0.07
    Activations Density 0.003%

    No Known Activations