© 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. 23989
    Prev
    Next
    INDEX
    Explanations

    Legal Aid

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

    critical area or topic

    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
    教學
    0.52
    i
    0.49
     glist
    0.46
    ＂
    0.44
     wonderful
    0.43
     ""
    0.43
     twin
    0.42
     ervan
    0.42
     kabar
    0.41
    ي
    0.41
    POSITIVE LOGITS
    ानुसार
    0.45
     Expenditures
    0.45
    म
    0.44
    olus
    0.43
    সের
    0.43
    ларни
    0.43
     Loans
    0.42
    ों
    0.42
    ைகளுக்கு
    0.41
    ometers
    0.41
    Activations Density 0.000%

    No Known Activations