© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1605
    Prev
    Next
    INDEX
    Explanations

    words starting with L

    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_40_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
    च्युअल
    0.39
    明確
    0.38
    Bromo
    0.38
    穹
    0.38
    芗
    0.36
    <unused5>
    0.35
    Multicolored
    0.35
    亜
    0.35
    ेडियम
    0.34
    ৩২
    0.34
    POSITIVE LOGITS
     L
    0.90
    L
    0.73
     l
    0.70
    abyrinth
    0.60
     ল
    0.52
     Л
    0.52
     ல
    0.51
    uminous
    0.50
    ifestyles
    0.50
    aptops
    0.50
    Activations Density 0.043%

    No Known Activations