© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54135
    Prev
    Next
    INDEX
    Explanations

    type described as

    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
     verschiedene
    -1.11
    annique
    -0.98
     différentes
    -0.98
     mwaka
    -0.98
     contribuer
    -0.97
    مقاله
    -0.97
    ORMAL
    -0.95
     différents
    -0.95
     travailler
    -0.94
     altre
    -0.94
    POSITIVE LOGITS
     in
    1.86
     from
    1.52
     described
    1.40
     as
    1.29
    expiresIn
    1.13
     above
    1.07
     mentioned
    1.03
     items
    0.98
     provided
    0.97
     jantung
    0.93
    Activations Density 0.020%

    No Known Activations