© 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. 16359
    Prev
    Next
    INDEX
    Explanations

    words that start with 'l' or 'lab'

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

    estate, summit, briefly, legally, intense, most

    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
     Imag
    0.43
     Lu
    0.40
    <0x0D>
    0.40
     Re
    0.39
     Laplacian
    0.39
    زی
    0.38
     agr
    0.38
     presum
    0.38
     capturing
    0.38
    0.38
    POSITIVE LOGITS
    我們
    0.44
    సారి
    0.43
    dividend
    0.43
     봄
    0.43
    澳洲
    0.42
     我們
    0.42
     우리는
    0.42
    зать
    0.41
     今年
    0.41
    渥
    0.41
    Activations Density 0.000%

    No Known Activations