© 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. 33625
    Prev
    Next
    INDEX
    Explanations

    nearest/closest + identifying noun

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

    explaining how to show options

    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
    on
    0.56
    ted
    0.50
    t
    0.50
    ?
    0.49
    of
    0.48
    united
    0.48
    ing
    0.47
    free
    0.47
    ahead
    0.47
    €˜
    0.46
    POSITIVE LOGITS
    సా
    0.50
    宽度
    0.49
     업체
    0.46
     যেহেতু
    0.46
    사가
    0.46
    这样一个
    0.46
     상황
    0.46
     వారు
    0.45
     এলাকার
    0.45
     পরিস্থিতি
    0.44
    Activations Density 0.000%

    No Known Activations