© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    http and www links

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

    website links

    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
    \_
    0.46
    ński
    0.38
     subscripts
    0.38
    侷
    0.37
    Ž
    0.36
    GISLATIVE
    0.35
     temperat
    0.35
     ÷
    0.34
     পদ্ধ
    0.34
    aarrggbb
    0.34
    POSITIVE LOGITS
     https
    3.17
    https
    3.05
     http
    2.98
    http
    2.80
     www
    2.31
    www
    1.98
    ttps
    1.86
    Https
    1.74
     Http
    1.45
    Http
    1.44
    Activations Density 0.324%

    No Known Activations