© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15284
    Prev
    Next
    INDEX
    Explanations

    usernames with suffixes

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

    The neuron fires strongly on capitalized proper names or handles (e.g. authors, usernames, or character‐style names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     and
    -1.26
     plena
    -1.22
     certe
    -1.19
    様な
    -1.19
     nuest
    -1.19
     mixta
    -1.17
    にします
    -1.16
    рить
    -1.16
     ulter
    -1.16
    ulkan
    -1.15
    POSITIVE LOGITS
     who
    1.70
    <bos>
    1.38
    inerary
    1.38
    桫
    1.32
    pherals
    1.30
    mmation
    1.29
    鹩
    1.29
    谥
    1.27
    unno
    1.23
     mostrarán
    1.23
    Activations Density 0.038%

    No Known Activations