© 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. 22-GEMMASCOPE-RES-131K
    7. 14212
    Prev
    Next
    INDEX
    Explanations

    market reports, forecasts, types

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

    The neuron principally detects numeric tokens—i.e. numbers and numeric data points (including decimals and percentages) in market‐report text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     about
    -1.16
     even
    -1.12
    orul
    -1.07
     their
    -1.04
     gewüns
    -1.03
     soon
    -1.02
    álna
    -1.02
     после
    -1.00
     Spielen
    -0.99
     erity
    -0.99
    POSITIVE LOGITS
     citroen
    1.23
     originale
    1.23
     volk
    1.20
     lepro
    1.19
     blin
    1.18
     koe
    1.16
     wein
    1.15
     eene
    1.15
     olie
    1.14
     laterale
    1.13
    Activations Density 0.002%

    No Known Activations