© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90804
    Prev
    Next
    INDEX
    Explanations

    short types and descriptions

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

    The neuron fires whenever it encounters the token “short” (e.g. the datatype or the word “short”).

    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
     tailored
    -0.97
     only
    -0.92
     less
    -0.91
    هاز
    -0.88
     those
    -0.86
     swiftly
    -0.82
     ended
    -0.81
     mera
    -0.78
     setTime
    -0.77
     Only
    -0.77
    POSITIVE LOGITS
    Short
    1.40
     SHORT
    1.32
     Short
    1.24
    short
    1.16
     short
    1.14
     MAX
    1.10
    MAX
    1.06
     maximale
    1.05
    අ
    0.99
     shorts
    0.95
    Activations Density 0.001%

    No Known Activations