© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22947
    Prev
    Next
    INDEX
    Explanations

    articles before job titles

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

    a followed by descriptive word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最後
    0.47
    횃
    0.45
     그의
    0.45
    最後の
    0.43
    詆
    0.42
     fileobj
    0.40
     답
    0.39
     يصبح
    0.38
    <0xAE>
    0.38
     njeg
    0.38
    POSITIVE LOGITS
     YouTuber
    0.59
     filmmaker
    0.53
     Australian
    0.48
     Pakistani
    0.46
     bipartisan
    0.46
     Veteran
    0.45
     University
    0.45
     journalist
    0.45
     twenty
    0.45
    ruar
    0.44
    Activations Density 0.059%

    No Known Activations