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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10640
    Prev
    Next
    INDEX
    Explanations

    markup tags and content

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

    code comments and explanations

    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_40_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
    s
    0.46
    faux
    0.42
     riches
    0.41
    lock
    0.40
    holder
    0.39
    g
    0.39
    promise
    0.39
    holy
    0.39
    were
    0.39
    fahren
    0.38
    POSITIVE LOGITS
    鉭
    0.42
    ⁡
    0.42
    歧
    0.40
     Bá
    0.39
    ⠀
    0.39
    芝
    0.39
    溇
    0.38
    ﹂
    0.38
     మి
    0.38
    ළු
    0.38
    Activations Density 0.017%

    No Known Activations