© 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. 143874
    Prev
    Next
    INDEX
    Explanations

    street addresses and locations

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

    teaching and guidance

    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
    ioc
    0.48
     finans
    0.45
     financed
    0.44
    '
    0.43
    ne
    0.43
     financi
    0.42
     ہوتی
    0.42
     analysing
    0.41
    vai
    0.41
     unlawfully
    0.41
    POSITIVE LOGITS
    Lesson
    0.51
    니다
    0.49
    牍
    0.47
     teacher
    0.46
     Lantern
    0.46
    肠
    0.46
    鳞
    0.46
    蕾
    0.46
    淙
    0.46
    FolderPath
    0.45
    Activations Density 0.001%

    No Known Activations