© 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. 38430
    Prev
    Next
    INDEX
    Explanations

    stopping or discontinuing

    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
     particular
    -1.24
    taining
    -1.02
     certain
    -0.98
     Particular
    -0.96
     flowers
    -0.96
     Gesicht
    -0.95
    𝚣
    -0.95
    ヨーグルト
    -0.95
    🐐
    -0.93
    เป๋า
    -0.93
    POSITIVE LOGITS
    Kenapa
    1.05
    //!
    1.03
    تعداد
    1.03
    étricas
    0.99
     jsem
    0.97
     télécommande
    0.97
    ément
    0.96
     disgusted
    0.96
    )=-\
    0.96
    ادامه
    0.96
    Activations Density 0.020%

    No Known Activations