© 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. 118535
    Prev
    Next
    INDEX
    Explanations

    prerequisites and features in larger context

    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
    应当
    -0.07
     except
    -0.06
     দুর্ভাগ্য
    -0.06
    应该
    -0.06
     Unfortunately
    -0.06
    except
    -0.06
    残念
    -0.06
    を除
    -0.06
     दि
    -0.06
     DAB
    -0.06
    POSITIVE LOGITS
     three
    0.07
    three
    0.06
     four
    0.06
     less
    0.06
    ੧
    0.06
     grew
    0.06
     communicating
    0.06
    ণ্ডের
    0.06
     грамо
    0.05
    ați
    0.05
    Activations Density 0.045%

    No Known Activations