© 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. 4966
    Prev
    Next
    INDEX
    Explanations

    plain and plane surfaces

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

    plain, plaintext, plane, plains

    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
     مجوز
    0.41
     capucha
    0.37
     కృ
    0.36
     widgets
    0.35
     Widgets
    0.35
    遏
    0.35
     estis
    0.35
    దర్శ
    0.34
     အတွ
    0.34
    笆
    0.34
    POSITIVE LOGITS
     plain
    3.88
     Plain
    3.81
    Plain
    3.81
    plain
    3.69
     plane
    3.47
    plane
    3.34
     Plane
    3.33
    Plane
    3.28
     plains
    3.23
     PLANE
    3.13
    Activations Density 0.110%

    No Known Activations