© 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. 53981
    Prev
    Next
    INDEX
    Explanations

    financial or investment terms

    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
    cac
    -0.80
    bi
    -0.77
    VAT
    -0.75
    xide
    -0.75
    concatenate
    -0.74
     Conde
    -0.74
     jede
    -0.74
     NIST
    -0.74
    leq
    -0.72
    wah
    -0.72
    POSITIVE LOGITS
     exclusions
    1.20
     exclusion
    1.14
    exclusion
    1.09
    investment
    1.08
     engagement
    1.04
    screens
    1.02
     Exclusion
    1.02
     investment
    1.02
    Voting
    1.00
    Exclusion
    0.98
    Activations Density 0.008%

    No Known Activations