© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3607
    Prev
    Next
    INDEX
    Explanations

    example or topic

    np_acts-logits-general · gemini-2.5-flash-lite

    requests or instructions directing the model to perform a task or generate content, often with explicit constraints or parameters.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     engl
    0.16
    अ
    0.16
     lata
    0.15
    <h3>
    0.15
    आज
    0.15
    Ö
    0.15
    äv
    0.15
    Ä
    0.15
     Menn
    0.14
    Æ
    0.14
    POSITIVE LOGITS
     및
    0.17
    ilize
    0.17
    цију
    0.15
     שה
    0.15
     调用
    0.15
     declarative
    0.15
     设置
    0.15
    Formatted
    0.14
     mutex
    0.14
     initialize
    0.14
    Activations Density 0.466%

    No Known Activations