© 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. 73180
    Prev
    Next
    INDEX
    Explanations

    Objective-C framework imports

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

    This neuron activates on numeric tokens (e.g. version numbers, numeric literals, counts) within the text.

    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
     his
    -0.93
    沾
    -0.92
     we
    -0.88
     Qualität
    -0.88
     also
    -0.86
     never
    -0.81
    苔
    -0.80
    künfte
    -0.80
    ।
    -0.79
    他的
    -0.79
    POSITIVE LOGITS
     جات
    0.99
    حوالہ
    0.98
    <!--<
    0.98
    袮
    0.96
     zilver
    0.96
     nominally
    0.95
     differentiates
    0.93
    LayoutManager
    0.92
     Brod
    0.91
    בה
    0.91
    Activations Density 0.034%

    No Known Activations