© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 90530
    Prev
    Next
    INDEX
    Explanations

    tick marks

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

    This neuron fires on code snippets that configure or reference chart axes (e.g. axis calls/attributes in plotting libraries).

    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
     Wink
    -0.85
    ziek
    -0.81
    aragus
    -0.78
     bagno
    -0.76
    Leon
    -0.75
     engines
    -0.75
     messaggio
    -0.74
     éxitos
    -0.74
     brug
    -0.74
     skole
    -0.74
    POSITIVE LOGITS
     tick
    1.17
     ticks
    1.13
    tick
    0.87
    ਸ਼
    0.81
     tic
    0.77
     TICK
    0.77
    oporosis
    0.77
     Tick
    0.77
     Weber
    0.74
     dług
    0.72
    Activations Density 0.008%

    No Known Activations