© 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. 118385
    Prev
    Next
    INDEX
    Explanations

    back into

    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
     после
    -0.08
     sonra
    -0.07
     after
    -0.07
     після
    -0.07
     depois
    -0.07
    之后
    -0.07
     이후
    -0.07
     après
    -0.07
     بعد
    -0.07
    后
    -0.07
    POSITIVE LOGITS
    と同じ
    0.06
     deduce
    0.06
    heath
    0.06
    rican
    0.06
     juice
    0.06
    Trước
    0.06
    此前
    0.06
     ధర
    0.06
     విషయం
    0.06
     iyong
    0.06
    Activations Density 0.004%

    No Known Activations