© 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. 49740
    Prev
    Next
    INDEX
    Explanations

    our offers

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

    This neuron fires strongly on section headers or titles—short, standalone lines (often in title case) that introduce sections of corporate or marketing 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
    రా
    -0.95
     преступ
    -0.94
    Ted
    -0.93
    علی
    -0.93
    كور
    -0.92
    vendors
    -0.90
     متحده
    -0.90
    spiele
    -0.89
    🎃
    -0.87
    spielen
    -0.87
    POSITIVE LOGITS
     our
    1.16
     you
    1.09
    Our
    1.05
     оказыва
    1.02
    常に
    0.99
     cualquier
    0.98
     discounts
    0.98
     любых
    0.97
     любые
    0.97
    Any
    0.93
    Activations Density 0.028%

    No Known Activations