© 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. 201754
    Prev
    Next
    INDEX
    Explanations

    imagery related to meaning

    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
    دم
    0.49
     التط
    0.48
    ప్‌
    0.47
    СП
    0.46
    سل
    0.45
     デザイン
    0.44
     優
    0.43
    AIM
    0.43
    superior
    0.42
    प्पा
    0.42
    POSITIVE LOGITS
     ';'
    0.46
    语义
    0.44
     hiển
    0.43
    હુ
    0.42
     okaza
    0.42
     clf
    0.42
    yj
    0.41
    nali
    0.41
     meadows
    0.41
    erie
    0.41
    Activations Density 0.004%

    No Known Activations