© 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. 116704
    Prev
    Next
    INDEX
    Explanations

    same, similar, copy

    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
    改變
    -0.07
    改变
    -0.07
     dieser
    -0.06
    修正
    -0.06
     fixe
    -0.06
     těchto
    -0.06
    給大家
    -0.06
     corrections
    -0.06
     deva
    -0.06
    change
    -0.06
    POSITIVE LOGITS
     hetzelfde
    0.07
     同じ
    0.07
     Same
    0.07
     same
    0.07
     similar
    0.06
     similaires
    0.06
    similar
    0.06
    same
    0.06
    Same
    0.06
     Kop
    0.06
    Activations Density 0.001%

    No Known Activations