© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 85843
    Prev
    Next
    INDEX
    Explanations

    The neuron detects common word endings and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    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
    er
    0.95
    en
    0.86
    ed
    0.75
    :
    0.73
    et
    0.69
    ew
    0.69
    y
    0.66
    o
    0.63
    es
    0.62
    am
    0.59
    POSITIVE LOGITS
    0.89
    ش
    0.72
    ियों
    0.65
    </h3>
    0.61
     festiv
    0.61
    öld
    0.60
     réduire
    0.59
     spate
    0.59
    शोर
    0.57
    年在
    0.57
    Activations Density 0.000%

    No Known Activations