© 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. 103156
    Prev
    Next
    INDEX
    Explanations

    bulls and bears

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

    The neuron fires on descriptive phrases about market participants—e.g. qualifiers like “too many,” “weak-handed,” “bulls,” and similar investor-sentiment terms.

    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
    堃
    -0.83
    ophanes
    -0.76
    parallel
    -0.73
     HIF
    -0.72
    অ
    -0.71
     Kunststoff
    -0.71
    ἀ
    -0.69
    위
    -0.68
     約
    -0.68
     Nab
    -0.67
    POSITIVE LOGITS
     bullish
    3.48
     bulls
    3.33
     Bull
    2.98
     bull
    2.94
    bull
    2.91
    Bull
    2.80
     bearish
    2.69
     Bulls
    2.64
     bears
    2.42
     BULL
    2.36
    Activations Density 0.025%

    No Known Activations