© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7893
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    please reach out for help

    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
     ď
    0.42
     iedere
    0.42
     Gif
    0.41
     Ans
    0.41
     σαν
    0.40
    র্ম
    0.40
     إذ
    0.40
    gif
    0.40
     Đấy
    0.40
     đấy
    0.38
    POSITIVE LOGITS
     XNUMX
    1.20
    NUMX
    1.17
     ​​
    0.67
    ​​
    0.66
     ​​​​
    0.62
    ​​​​
    0.53
    NUM
    0.49
    XX
    0.47
    ////////////////
    0.45
     ”,
    0.45
    Activations Density 0.005%

    No Known Activations