© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 56694
    Prev
    Next
    INDEX
    Explanations

    origin, purpose, existence

    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
    2
    0.44
     आधे
    0.42
    8
    0.42
    4
    0.41
    دهای
    0.41
     orange
    0.40
     eighteenth
    0.40
    📷
    0.39
    shared
    0.39
     standardized
    0.38
    POSITIVE LOGITS
    行星
    0.47
    ీ
    0.43
    אָ
    0.43
     филосо
    0.42
    柰
    0.42
    шит
    0.41
     философия
    0.40
     космо
    0.40
    㚘
    0.40
     формула
    0.39
    Activations Density 0.000%

    No Known Activations