© 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. 15551
    Prev
    Next
    INDEX
    Explanations

    mut followed by Kaiser or -ated / -ants

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

    The neuron fires on occurrences of the “mut” root (as in mutant, mutable, mutated, etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    茈
    -2.09
    鲵
    -2.06
     zahlreichen
    -2.05
    맷
    -2.02
    ཽ
    -1.99
    絝
    -1.99
    𝄆
    -1.98
     potrebné
    -1.96
    ሯ
    -1.96
     которы
    -1.94
    POSITIVE LOGITS
     this
    2.16
    m
    1.95
    </h1>
    1.94
    ان
    1.94
    What
    1.90
    大多数
    1.83
    );
    1.81
    This
    1.80
    an
    1.79
    c
    1.79
    Activations Density 0.000%

    No Known Activations