© 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. 99245
    Prev
    Next
    INDEX
    Explanations

    logged in state

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

    The neuron fires on mentions of “logged” (as in “logged in”) indicating user authentication or session state.

    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
    素晴らしい
    -2.95
    u
    -2.67
     be
    -2.61
    缡
    -2.59
    z
    -2.53
    几
    -2.52
     rencontre
    -2.44
    \
    -2.39
    และ
    -2.33
    {
    -2.33
    POSITIVE LOGITS
    <bos>
    3.58
    メニューは
    2.88
    the
    2.64
    𞤢
    2.64
    nachron
    2.58
    之后的
    2.41
    是这样
    2.39
    眼下
    2.39
    ⃚
    2.33
    Ꮸ
    2.30
    Activations Density 0.003%

    No Known Activations