© 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. 70406
    Prev
    Next
    INDEX
    Explanations

    ATM machine

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

    intimate moment

    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
    دون
    0.47
     programmed
    0.46
     abogado
    0.45
    平成
    0.43
    Ap
    0.42
     spreadsheets
    0.42
    程序员
    0.41
    (
    0.41
    跌
    0.41
    را
    0.41
    POSITIVE LOGITS
     духо
    0.54
     Bunny
    0.49
     双
    0.46
    స్వా
    0.46
     Thị
    0.44
     local
    0.43
    ompany
    0.43
     Mandala
    0.43
     ፍ
    0.42
     Bil
    0.42
    Activations Density 0.000%

    No Known Activations