© 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. 130264
    Prev
    Next
    INDEX
    Explanations

    either express or implied

    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
     รัก
    -0.07
     निरंतर
    -0.07
     சிலர்
    -0.07
     наша
    -0.06
     нам
    -0.06
    을
    -0.06
    当地
    -0.06
    當地
    -0.06
     наш
    -0.06
     nostre
    -0.06
    POSITIVE LOGITS
     multiple
    0.07
     چندین
    0.07
    multiple
    0.07
    """
    0.06
    тпу
    0.06
     VEGFR
    0.06
     grouped
    0.06
    全ての
    0.06
    複数の
    0.06
     vaulted
    0.06
    Activations Density 0.002%

    No Known Activations