© 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-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 347
    Prev
    Next
    INDEX
    Explanations

    down a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    س
    0.80
    ۰
    0.79
    <0x80>
    0.77
    с
    0.76
    0
    0.71
    ？”
    0.70
    Mountains
    0.67
    Putin
    0.66
    M
    0.64
    F
    0.64
    POSITIVE LOGITS
     of
    1.00
    o
    0.95
     on
    0.92
     is
    0.90
    ન
    0.87
    a
    0.86
    n
    0.83
    야
    0.74
    ed
    0.73
    an
    0.71
    Activations Density 0.752%

    No Known Activations