© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34636
    Prev
    Next
    INDEX
    Explanations

    Prop, Paul, von, words, Rank, touch, warfare, ism

    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
    V
    0.93
    P
    0.85
    나
    0.81
    A
    0.79
    D
    0.75
    rn
    0.73
    L
    0.73
    né
    0.72
    utiérrez
    0.72
    ట్
    0.68
    POSITIVE LOGITS
    :
    0.88
    '
    0.79
    ung
    0.65
    いますが
    0.64
    ۰
    0.64
    ↵
    0.64
    साठी
    0.62
     شی
    0.62
    şı
    0.61
    ğini
    0.61
    Activations Density 0.001%

    No Known Activations