© 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. 118743
    Prev
    Next
    INDEX
    Explanations

    final words or punctuation

    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
     these
    -0.06
    These
    -0.06
     একান্ত
    -0.06
     These
    -0.06
     इन्हीं
    -0.06
     নিঃসন্দেহে
    -0.06
     estás
    -0.06
     estas
    -0.06
    these
    -0.06
     intest
    -0.05
    POSITIVE LOGITS
     علشان
    0.07
    вичай
    0.07
     wobei
    0.07
    就可以
    0.07
     عشان
    0.07
    任何
    0.07
     sostenible
    0.06
     длиной
    0.06
     سپس
    0.06
     zlo
    0.06
    Activations Density 0.004%

    No Known Activations