© 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. 3396
    Prev
    Next
    INDEX
    Explanations

    Lewis exact

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

    exact match

    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
    ールの
    0.43
     illo
    0.43
     ကု
    0.42
     Kuo
    0.41
    逖
    0.41
    ILIA
    0.39
    ilia
    0.39
     Elys
    0.38
    咪
    0.38
     Roughly
    0.37
    POSITIVE LOGITS
     unknown
    0.59
    precise
    0.59
     precise
    0.57
    unknown
    0.57
     exact
    0.52
    Unknown
    0.49
    EX
    0.47
     dokład
    0.47
    精确
    0.46
    精准
    0.45
    Activations Density 0.000%

    No Known Activations