© 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. 143087
    Prev
    Next
    INDEX
    Explanations

    gif valentine

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

    punctuation indicating interruption or aside

    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
    你怎么
    0.49
     Have
    0.47
     médicale
    0.43
    षेक
    0.42
    ளிக்க
    0.41
    笔记本
    0.41
     Η
    0.40
     Harga
    0.40
    لیک
    0.40
     Saturdays
    0.40
    POSITIVE LOGITS
    因為
    0.49
     conectar
    0.48
    RP
    0.48
    DIALOG
    0.47
     conecta
    0.46
    শ
    0.45
     align
    0.44
    Beginning
    0.43
    Position
    0.43
    PRESSED
    0.43
    Activations Density 0.000%

    No Known Activations