© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80869
    Prev
    Next
    INDEX
    Explanations

    as published by

    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_34/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
     manifests
    -1.16
    cinhas
    -1.13
    诞生
    -1.09
     logistique
    -1.08
     emporio
    -1.08
     enfance
    -1.02
     médaille
    -1.02
     sué
    -1.02
     руке
    -1.02
    voyez
    -1.02
    POSITIVE LOGITS
     a
    1.48
     soon
    1.38
     follows
    1.33
     though
    1.27
     будто
    1.26
     well
    1.25
     usual
    1.23
     também
    1.23
    ïdes
    1.18
     минимум
    1.18
    Activations Density 0.048%

    No Known Activations