© 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. 35934
    Prev
    Next
    INDEX
    Explanations

    is there | is she | 20

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

    listing conjunctions and phrases

    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
     தற்போது
    0.49
     वर्तमान
    0.46
     現在
    0.46
     म्यु
    0.45
     smartwatch
    0.44
     デ
    0.44
     RON
    0.44
     ቦታ
    0.44
    聰
    0.44
    ᆻ
    0.43
    POSITIVE LOGITS
     travelled
    0.50
    ایش
    0.49
    的过程中
    0.47
     to
    0.47
    صله
    0.43
    说法
    0.42
    项目中
    0.42
    贮
    0.42
     onları
    0.41
    表达
    0.41
    Activations Density 0.000%

    No Known Activations