© 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. 35606
    Prev
    Next
    INDEX
    Explanations

    deletion or destruction

    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
     estrena
    -1.25
    𐀀
    -1.21
     damen
    -1.20
     Traité
    -1.13
     formen
    -1.10
     confirmó
    -1.09
    向了
    -1.09
     volverá
    -1.08
     mantend
    -1.05
     prevé
    -1.05
    POSITIVE LOGITS
     or
    1.28
     so
    1.08
     if
    0.97
     diligent
    0.94
     razem
    0.93
     chiam
    0.91
     piernas
    0.91
     partial
    0.91
     no
    0.90
    なんですよ
    0.89
    Activations Density 0.002%

    No Known Activations