© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5814
    Prev
    Next
    INDEX
    Explanations

    with

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

    introducing structured 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_31_width_262k_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
    ،
    0.47
     ؟
    0.40
    ؛
    0.39
    ؟
    0.39
    ؟.
    0.38
     ،
    0.37
    ۔
    0.36
    ၊
    0.36
    ؟!
    0.35
    ፣
    0.35
    POSITIVE LOGITS
     with
    0.66
    with
    0.64
     với
    0.57
     waarbij
    0.54
     whereby
    0.52
     עם
    0.52
     which
    0.51
    dengan
    0.51
    which
    0.50
     cuya
    0.50
    Activations Density 0.701%

    No Known Activations