© 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. 120267
    Prev
    Next
    INDEX
    Explanations

    html tags

    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
     is
    -0.09
     may
    -0.08
     것은
    -0.08
     puede
    -0.08
     может
    -0.07
     огром
    -0.07
    ведение
    -0.07
     स्वादिष्ट
    -0.07
     другими
    -0.07
     Puede
    -0.07
    POSITIVE LOGITS
     |
    0.06
     !
    0.06
     l
    0.06
     ....
    0.05
    きっかけ
    0.05
    |
    0.05
     ?
    0.05
     —
    0.05
     --
    0.05
     !!
    0.05
    Activations Density 0.001%

    No Known Activations