© 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. 53995
    Prev
    Next
    INDEX
    Explanations

    instructions on settlement

    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
    Luckily
    0.45
    ్ఞ
    0.45
     เหมาะ
    0.44
    run
    0.44
    දහ
    0.44
    onos
    0.44
    together
    0.43
    о
    0.42
    smaller
    0.42
    ла
    0.42
    POSITIVE LOGITS
    ामान्य
    0.52
    词
    0.45
     Parental
    0.45
     judg
    0.44
     intentional
    0.44
     κινη
    0.43
     restructured
    0.43
    证
    0.43
     widened
    0.43
    被告
    0.43
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.