© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17326
    Prev
    Next
    INDEX
    Explanations

    words in quotes or sentences

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

    words or phrases in quotes

    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_53_width_65k_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
     “‘
    1.82
     “”
    1.55
    ‘
    1.55
    .’”
    1.51
     ‘‘
    1.49
    (“
    1.48
     (‘
    1.47
     ‘
    1.46
    …’
    1.46
    —“
    1.45
    POSITIVE LOGITS
     "
    2.56
     '
    2.41
     "'
    2.03
    ,"
    2.00
     ".
    1.92
    '"
    1.90
    ".
    1.88
     ",
    1.83
    。"
    1.83
    ',"
    1.81
    Activations Density 0.126%

    No Known Activations