© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58245
    Prev
    Next
    INDEX
    Explanations

    Arachnoid, rsp, Lyn

    np_acts-logits-general · gemini-2.5-flash-lite

    programming and technical identifiers like 'rsp', 'Lyn', and memory addresses.

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi

    The neuron fires on “stand‐out” tokens that carry internal uppercase (or all‐caps) letters—e.g. acronyms, register names (rsp/RSP), code identifiers, or proper names like Lyn—not on ordinary words.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    3
    -3.31
    on
    -2.94
    From
    -2.86
    ра
    -2.66
    With
    -2.59
    <td>
    -2.56
    In
    -2.55
    5
    -2.52
    with
    -2.45
    1
    -2.45
    POSITIVE LOGITS
    籐
    3.42
    骘
    2.84
    ㉗
    2.70
    งิน
    2.61
    ㉖
    2.61
    ")));
    2.59
    
    2.56
    ୩
    2.53
    ᨈ
    2.47
    ↑↑↑</
    2.45
    Activations Density 0.019%

    No Known Activations