© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 13879
    Prev
    Next
    INDEX
    Explanations

    start of sentences/clauses

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

    i will, i can, i understand, i'm

    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
     ด
    0.52
     จำนวน
    0.51
     അദ്ദേ
    0.50
     numeri
    0.49
     nummer
    0.48
     त्यात
    0.47
     และ
    0.46
     इसमें
    0.46
     ਨ
    0.45
    าด
    0.45
    POSITIVE LOGITS
    oretically
    1.03
    odore
    0.70
    :
    0.59
    скольку
    0.54
     BUT
    0.51
    смотря
    0.49
    1
    0.49
    দের
    0.45
    oltre
    0.44
    8
    0.43
    Activations Density 1.073%

    No Known Activations