© 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. 2011
    Prev
    Next
    INDEX
    Explanations

    slashes and plus-minus indicators

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

    punctuation and symbols

    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
    或者是
    0.42
    和其他
    0.41
    或其他
    0.40
     وغير
    0.38
     "${
    0.37
    或是
    0.37
    Autowired
    0.35
    䬲
    0.35
     ${{
    0.34
     $("
    0.34
    POSITIVE LOGITS
    /
    1.96
    –
    1.41
    ／
    1.30
    -/
    1.18
    ‒
    1.06
     /
    1.04
    /-
    1.01
    ・
    1.01
    ־
    1.01
    ⁄
    0.98
    Activations Density 0.779%

    No Known Activations