© 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. 5150
    Prev
    Next
    INDEX
    Explanations

    magic number

    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
    N
    0.54
    U
    0.48
    K
    0.46
     dư
    0.44
     president
    0.41
    metrics
    0.41
    文
    0.41
    T
    0.41
     controlar
    0.41
    施工
    0.39
    POSITIVE LOGITS
    👳
    0.50
     একজনের
    0.50
     インド
    0.50
    لک
    0.49
    ☺
    0.49
    ）・
    0.48
    reys
    0.46
     丿
    0.46
     Considering
    0.46
     ವಿಶ್ವ
    0.46
    Activations Density 0.000%

    No Known Activations