© 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. 83068
    Prev
    Next
    INDEX
    Explanations

    your booth, you enjoy, that investing

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

    shadow fell

    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
    fron
    0.47
     ጡ
    0.47
    算出
    0.46
    bodied
    0.45
     რო
    0.44
    ሖ
    0.44
     రో
    0.44
    moins
    0.44
     ভবিষ্য
    0.43
     recovered
    0.43
    POSITIVE LOGITS
    n
    0.68
    0
    0.58
    to
    0.54
    アメリカ
    0.54
    문
    0.53
    О
    0.52
    ுமி
    0.50
    ন
    0.50
    ב
    0.49
    MAR
    0.49
    Activations Density 0.000%

    No Known Activations