© 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. 1906
    Prev
    Next
    INDEX
    Explanations

    9 followed by 9

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

    nine

    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
    <unused68>
    0.51
     XVIII
    0.47
     eighteenth
    0.47
    <unused74>
    0.46
    <unused36>
    0.45
    <end_of_turn>
    0.45
     XVII
    0.43
     xviii
    0.40
     viii
    0.39
     七
    0.39
    POSITIVE LOGITS
    ９
    2.55
    9
    2.36
     ninety
    2.30
     девя
    2.27
     ۹
    2.25
    <0xBF>
    2.16
     ९
    2.16
    九
    2.16
    ۹
    2.16
     nine
    2.09
    Activations Density 0.466%

    No Known Activations