© 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. 33937
    Prev
    Next
    INDEX
    Explanations

    hallway, Hallman, Halling, Hall cell

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

    This neuron activates on any token containing the substring “hall” (e.g. Hall, hallway, 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_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
    诓
    -2.64
    该如何
    -2.58
    腚
    -2.52
     และ
    -2.48
    谖
    -2.47
    邺
    -2.45
     miſ
    -2.41
     หรือ
    -2.39
     男人
    -2.38
     mauva
    -2.36
    POSITIVE LOGITS
    \
    2.69
    用
    2.53
    是
    2.41
     eind
    2.41
    去
    2.39
    𓆜
    2.30
    ☑️
    2.30
    数据
    2.27
    ');
    2.22
     '
    2.19
    Activations Density 0.016%

    No Known Activations