© 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-262K
    7. 103674
    Prev
    Next
    INDEX
    Explanations

    signing in

    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_262k_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
     the
    0.67
     as
    0.65
    o
    0.63
    t
    0.61
    Item
    0.60
     about
    0.59
    ন
    0.57
    as
    0.56
     de
    0.54
    ber
    0.54
    POSITIVE LOGITS
    쯜
    0.63
    אנ
    0.58
     setSnackbar
    0.55
    ཾ
    0.55
    輋
    0.52
     coef
    0.52
    झाने
    0.51
    tBleStatus
    0.50
    ግብ
    0.50
    룺
    0.50
    Activations Density 0.000%

    No Known Activations