© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8455
    Prev
    Next
    INDEX
    Explanations

    site, websites, blogs

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

    captcha solvers

    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
     interp
    0.39
     interstices
    0.38
     ECONOM
    0.37
     subscripts
    0.37
    ________
    0.37
    というか
    0.37
     helm
    0.36
    此前
    0.36
     ops
    0.36
     president
    0.36
    POSITIVE LOGITS
    사이트
    0.60
     출
    0.57
    Https
    0.57
    https
    0.56
     https
    0.56
    ⅾ
    0.56
    Ⲥ
    0.54
    Ⴝ
    0.54
    ⅼ
    0.54
    ⲟ
    0.54
    Activations Density 0.127%

    No Known Activations