© 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. 117780
    Prev
    Next
    INDEX
    Explanations

    exit barrier tunneling Rydberg scattering mode

    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
     시간
    -0.06
    isolate
    -0.06
     time
    -0.06
     नष्ट
    -0.06
     홈페이지
    -0.06
    剩下的
    -0.06
    ठीक
    -0.06
     vreme
    -0.06
    හාර
    -0.06
     штра
    -0.06
    POSITIVE LOGITS
     liaison
    0.06
     அருகில்
    0.06
     carri
    0.06
     cannot
    0.06
    urilor
    0.06
     incumbents
    0.05
     prêts
    0.05
     ready
    0.05
    buying
    0.05
     subsidy
    0.05
    Activations Density 0.001%

    No Known Activations