© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26683
    Prev
    Next
    INDEX
    Explanations

    sales and revenue trends

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

    The neuron flags words that describe strong quantitative shifts or extremes—e.g. “surging,” “accelerating,” “falling,” “decimate,” “rebound,” or “higher.”

    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
     mismas
    -1.27
     tillegg
    -1.22
     özellikleri
    -1.21
     dvě
    -1.16
     cedo
    -1.15
    Diseño
    -1.15
     deği
    -1.14
    还得
    -1.10
    pictured
    -1.09
    聼
    -1.08
    POSITIVE LOGITS
     both
    2.11
     its
    1.93
     our
    1.68
     prices
    1.55
     in
    1.53
     overall
    1.48
     rates
    1.45
     total
    1.38
     revenues
    1.37
     the
    1.34
    Activations Density 0.055%

    No Known Activations