© 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. 34-GEMMASCOPE-RES-131K
    7. 57193
    Prev
    Next
    INDEX
    Explanations

    UI action connections

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

    The neuron activates on numeric tokens (literal numbers) in the code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     saka
    -0.76
    питы
    -0.74
    สาร
    -0.74
    თ
    -0.74
     фона
    -0.73
     кам
    -0.72
     Zac
    -0.72
    ığı
    -0.71
     soluble
    -0.71
    ເ
    -0.71
    POSITIVE LOGITS
    IBAction
    1.91
     actions
    1.19
     IB
    1.18
    Actions
    1.14
     IBOutlet
    1.13
     Actions
    1.10
     IBA
    1.07
    actions
    1.06
     action
    0.96
    Outlet
    0.96
    Activations Density 0.035%

    No Known Activations