© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 79858
    Prev
    Next
    INDEX
    Explanations

    trading and currency pairs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     le
    0.46
     photoshoot
    0.46
     a
    0.46
     as
    0.45
     im
    0.44
     jego
    0.43
     পানিতে
    0.42
     hydroelectric
    0.41
    <0x94>
    0.41
     pemb
    0.41
    POSITIVE LOGITS
     표준
    0.47
    бычно
    0.47
     역사
    0.46
    Ნ
    0.45
     הן
    0.42
     गरीबों
    0.41
     пережи
    0.41
     смысле
    0.41
    越来越
    0.41
    很少
    0.41
    Activations Density 0.021%

    No Known Activations