© 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. 13898
    Prev
    Next
    INDEX
    Explanations

    future continuation

    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
    Schriften
    -1.06
    spielen
    -1.00
     предыду
    -1.00
     pernah
    -0.98
     ادبی
    -0.98
     tost
    -0.97
    絝
    -0.94
     тогда
    -0.93
     externe
    -0.92
     鸭
    -0.91
    POSITIVE LOGITS
     will
    2.88
     continue
    1.97
     continuing
    1.86
     next
    1.85
     continued
    1.52
     remain
    1.41
     continues
    1.39
     still
    1.33
     already
    1.29
     continuará
    1.28
    Activations Density 0.026%

    No Known Activations