© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54095
    Prev
    Next
    INDEX
    Explanations

    different kinds

    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
     manually
    0.47
    ט
    0.45
    轉換
    0.43
     Only
    0.43
    鸡蛋
    0.43
    بط
    0.43
     eraser
    0.43
     sólo
    0.42
    で使用
    0.42
    ट
    0.42
    POSITIVE LOGITS
    akti
    0.49
    rawdę
    0.47
    yesters
    0.47
    highscore
    0.46
    gal
    0.45
    ceptions
    0.44
     पिस्टल
    0.43
    gladbach
    0.43
     enraged
    0.42
    akrishna
    0.42
    Activations Density 0.002%

    No Known Activations