© 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. 3685
    Prev
    Next
    INDEX
    Explanations

    end of sentences with specific subsequent words

    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
    t
    0.87
    h
    0.80
    d
    0.74
    k
    0.71
    f
    0.70
    c
    0.64
    n
    0.63
    ia
    0.62
    e
    0.60
    א
    0.58
    POSITIVE LOGITS
     ؟
    0.61
    يد
    0.56
    ۔
    0.55
    0.54
    )،
    0.51
    ým
    0.50
    ة
    0.50
    ؟
    0.50
    До
    0.50
     ؛
    0.49
    Activations Density 0.089%

    No Known Activations