© 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. 16-GEMMASCOPE-2-RES-262K
    4. 21188
    Prev
    Next
    INDEX
    Explanations

    English football clubs and matches

    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_16_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
    DUCTION
    0.80
     de
    0.79
     as
    0.79
     with
    0.77
     about
    0.74
     IN
    0.69
    NING
    0.68
     Q
    0.66
     da
    0.65
     do
    0.65
    POSITIVE LOGITS
    lvl
    0.66
    ላለ
    0.64
    atoti
    0.59
    。
    0.55
    勢
    0.54
    重要な
    0.54
    lendi
    0.53
    lng
    0.53
    άζ
    0.53
     restricts
    0.53
    Activations Density 0.000%

    No Known Activations