© 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. 73330
    Prev
    Next
    INDEX
    Explanations

    financial movements and indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    عامل
    -0.92
    cargas
    -0.90
     senjata
    -0.85
     from
    -0.84
     utilizzati
    -0.82
     ibunya
    -0.82
    cambios
    -0.81
     pembunuhan
    -0.80
     Aktivitäten
    -0.80
     their
    -0.79
    POSITIVE LOGITS
     was
    1.24
     gained
    1.00
    GAIN
    0.99
     GAIN
    0.94
     gain
    0.93
     shed
    0.93
     hemoglobin
    0.92
     traded
    0.92
    qui
    0.91
     ticked
    0.91
    Activations Density 0.011%

    No Known Activations