© 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. 58849
    Prev
    Next
    INDEX
    Explanations

    numbered list items

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

    list items starting with 1

    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
     aig
    0.49
    濺
    0.45
     ("",
    0.44
    מס
    0.41
     tattoo
    0.40
    數據
    0.39
    』（
    0.39
    ोनेशिया
    0.39
    ུང་
    0.39
    <unused1014>
    0.39
    POSITIVE LOGITS
    oooooooo
    0.55
    i
    0.54
    У
    0.53
    cknowled
    0.52
    ️⃣
    0.51
    ooo
    0.50
    oooo
    0.50
    ۱
    0.49
    ¿
    0.49
    ि
    0.47
    Activations Density 0.046%

    No Known Activations