© 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. 119196
    Prev
    Next
    INDEX
    Explanations

    wrong with this sentence

    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
    为了
    -0.07
     structure
    -0.06
     statistique
    -0.06
     pleg
    -0.06
     predictions
    -0.06
    為了
    -0.06
     statistics
    -0.06
     uncertainties
    -0.06
    influence
    -0.06
     consequ
    -0.06
    POSITIVE LOGITS
    正直
    0.07
     좋아하는
    0.06
     attaching
    0.06
    meet
    0.06
     Protect
    0.06
     assigns
    0.06
     отца
    0.06
     люби
    0.06
     listy
    0.06
    οι
    0.06
    Activations Density 0.046%

    No Known Activations