© 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. 120686
    Prev
    Next
    INDEX
    Explanations

    comprehensive and extensive analysis

    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
    包括
    -0.07
     mett
    -0.07
     મોટી
    -0.07
     Baku
    -0.07
     seperti
    -0.06
    如
    -0.06
    めちゃ
    -0.06
     participants
    -0.06
    }></
    -0.06
     bezoek
    -0.06
    POSITIVE LOGITS
    รั่ง
    0.06
     manifestly
    0.05
     ausführ
    0.05
     continually
    0.05
     했
    0.05
     तरुणा
    0.05
     mencipt
    0.05
     கால்
    0.05
     کمتر
    0.05
     trouvait
    0.05
    Activations Density 0.014%

    No Known Activations