© 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. 17233
    Prev
    Next
    INDEX
    Explanations

    numbers and names

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

    numbers

    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
     Two
    0.57
     milliers
    0.55
     دو
    0.53
    Two
    0.52
     Thousands
    0.52
    thousands
    0.50
    倆
    0.47
    Thousands
    0.46
     両
    0.45
     இருவரும்
    0.45
    POSITIVE LOGITS
     thirteen
    3.14
     eleven
    3.13
     nine
    3.08
     fourteen
    3.06
     eight
    2.92
     seventeen
    2.92
     twelve
    2.91
     sixteen
    2.91
     seven
    2.81
     eighteen
    2.73
    Activations Density 0.454%

    No Known Activations