© 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. 165689
    Prev
    Next
    INDEX
    Explanations

    personal information, local partners, branding firm

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

    make predictions

    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
    c
    0.49
     aliases
    0.44
    感受到
    0.44
     osm
    0.43
    主要是
    0.42
     ordained
    0.41
    -
    0.41
    س
    0.40
     aliens
    0.40
     conspiracies
    0.40
    POSITIVE LOGITS
     ២
    0.57
    ing
    0.56
     bút
    0.53
    ة
    0.53
    粞
    0.53
     この
    0.51
     পদ্ধ
    0.51
     vở
    0.51
    <unused437>
    0.51
     эш
    0.50
    Activations Density 0.000%

    No Known Activations