© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169938
    Prev
    Next
    INDEX
    Explanations

    rule out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SQLAlchemy
    0.52
    會有
    0.51
    ט
    0.48
    ่
    0.47
    it
    0.47
    হেতু
    0.47
    at
    0.46
    as
    0.46
     fitur
    0.46
    ท
    0.44
    POSITIVE LOGITS
     radicals
    0.51
     radicales
    0.50
     délais
    0.49
     hillside
    0.48
     factorización
    0.48
     महंगी
    0.46
    波动
    0.46
     लगता
    0.45
     faith
    0.44
     high
    0.44
    Activations Density 0.002%

    No Known Activations