© 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. 10-GEMMASCOPE-RES-131K
    7. 7067
    Prev
    Next
    INDEX
    Explanations

    insect bites

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

    The neuron activates for the start of answers in Q&A format, particularly when following a question with a colon and line break.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Geschwindigkeit
    -1.41
    gencia
    -1.29
    alism
    -1.26
    getStart
    -1.26
     Também
    -1.26
    請問
    -1.25
    Вход
    -1.24
    ኹ
    -1.23
    cazione
    -1.23
    🏟
    -1.22
    POSITIVE LOGITS
    .
    1.48
    0
    1.39
     although
    1.36
    4
    1.34
     despite
    1.34
    9
    1.33
    {
    1.31
    1
    1.30
    5
    1.30
    ."
    1.29
    Activations Density 0.169%

    No Known Activations