© 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. 154501
    Prev
    Next
    INDEX
    Explanations

    ambulatory surgical centers

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

    research and technical information

    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
    人の
    0.53
    ﾌ
    0.52
    勅
    0.51
    ｽ
    0.50
     nessuna
    0.49
    МІ
    0.49
    дина
    0.48
     degli
    0.48
    ಾ
    0.47
    猶
    0.46
    POSITIVE LOGITS
    њ
    0.44
     transformación
    0.42
    asch
    0.42
     पला
    0.42
    底层
    0.42
     dries
    0.41
    cts
    0.41
     peeled
    0.41
    吉祥
    0.40
    banks
    0.40
    Activations Density 0.000%

    No Known Activations