© 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. 15066
    Prev
    Next
    INDEX
    Explanations

    made-to-order

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

    crafting, reduction, fever, materials

    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
    a
    0.57
    chart
    0.51
    al
    0.51
    tra
    0.48
    tidak
    0.47
    xxx
    0.47
    of
    0.46
    ario
    0.46
    ata
    0.46
    una
    0.46
    POSITIVE LOGITS
     Diamond
    0.46
    お金
    0.46
    碎
    0.45
    濂
    0.45
    肾
    0.44
     diamonds
    0.44
     corneal
    0.44
    俦
    0.44
     rewind
    0.43
    毙
    0.43
    Activations Density 0.000%

    No Known Activations