© 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. 69312
    Prev
    Next
    INDEX
    Explanations

    body parts, media, legal, and technical terms

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

    socket set

    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
     t
    0.63
     d
    0.55
     g
    0.54
    th
    0.54
     oby
    0.54
     k
    0.53
    در
    0.53
     z
    0.52
    9
    0.52
     WITH
    0.51
    POSITIVE LOGITS
     발생하는
    0.49
    ]।
    0.49
    ichtet
    0.46
    ।
    0.46
    ሉት
    0.45
    )।
    0.45
    포츠
    0.45
    ুক্ত
    0.43
    έσ
    0.42
    আন্ত
    0.42
    Activations Density 0.000%

    No Known Activations