Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B
    3. 16-GEMMASCOPE-2-RES-16K
    4. 793
    Prev
    Next
    INDEX
    Explanations

    ian Generator

    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_16_width_16k_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
    A
    0.82
     I
    0.80
    f
    0.72
    matic
    0.71
    ses
    0.69
    0
    0.69
    worldly
    0.65
    wissenschaft
    0.65
    scape
    0.64
    W
    0.63
    POSITIVE LOGITS
     كان
    0.99
     centaines
    0.96
     be
    0.94
     。
    0.94
     في
    0.90
     trabajo
    0.83
     لي
    0.83
    ન
    0.83
     deux
    0.82
     plusieurs
    0.82
    Activations Density 1.404%

    No Known Activations