© 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. 15413
    Prev
    Next
    INDEX
    Explanations

    android layout attributes

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

    This neuron activates on numeric literal tokens (e.g. dimensions and size values) in code snippets.

    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
     that
    -1.48
     (
    -1.47
     from
    -1.46
    贋
    -1.43
     we
    -1.40
     tecnologias
    -1.38
    信念
    -1.36
     there
    -1.30
    bbons
    -1.26
     in
    -1.24
    POSITIVE LOGITS
    ia
    1.15
    er
    1.11
    l
    1.10
    ۔
    1.08
    u
    1.05
    era
    1.04
    ela
    1.03
    ne
    1.03
     ""
    1.03
    la
    1.02
    Activations Density 0.001%

    No Known Activations