© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30028
    Prev
    Next
    INDEX
    Explanations

    The neuron detects units, numbers after delimiters, or calculus terms

    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_7_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
    am
    0.72
    ка
    0.69
    。
    0.69
    h
    0.67
    يل
    0.67
    ne
    0.65
    на
    0.65
    ش
    0.64
    ج
    0.63
    ق
    0.63
    POSITIVE LOGITS
     that
    0.57
     outperforms
    0.48
     surpasses
    0.47
    ēja
    0.46
     surpluses
    0.46
     if
    0.46
     perceives
    0.46
     IPO
    0.46
    ிடம்
    0.46
     seduced
    0.46
    Activations Density 0.026%

    No Known Activations