© 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. 72077
    Prev
    Next
    INDEX
    Explanations

    credit ratings and stock downgrades

    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_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
     włosów
    -1.26
     מים
    -1.15
     گیاه
    -1.13
     sparen
    -1.11
    想要
    -1.10
    ERSHIP
    -1.06
     merav
    -1.05
     Theologie
    -1.05
     כדי
    -1.05
    Didn
    -1.04
    POSITIVE LOGITS
    ּוֹ
    1.96
    ִּ
    1.86
    ַּ
    1.71
    וּ
    1.66
     rating
    1.54
     ratings
    1.51
    ֶּ
    1.48
     analysts
    1.39
    ְּ
    1.34
     analyst
    1.34
    Activations Density 0.002%

    No Known Activations