© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32514
    Prev
    Next
    INDEX
    Explanations

    fishing lines and tackle

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

    The neuron spikes on brand- or product-style names and the surrounding promotional sales copy.

    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
    дон
    -0.81
    gero
    -0.80
     Fett
    -0.77
     dzie
    -0.77
     Köz
    -0.75
     Brentford
    -0.75
    ginate
    -0.74
    alım
    -0.74
    oform
    -0.73
    덟
    -0.73
    POSITIVE LOGITS
     line
    1.07
     abrasion
    1.03
     mon
    1.01
     lines
    0.93
     mono
    0.93
     mainline
    0.91
     leader
    0.86
     fluor
    0.85
     test
    0.83
     моно
    0.82
    Activations Density 0.011%

    No Known Activations