© 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. 35831
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    bte
    -1.05
    鼍
    -1.02
     ఈ
    -0.99
    iI
    -0.99
     zahrani
    -0.98
     uitzicht
    -0.98
    杢
    -0.97
    戗
    -0.97
     bekijken
    -0.96
    yorsunuz
    -0.96
    POSITIVE LOGITS
     with
    1.66
     shewn
    1.04
    خم
    1.02
    With
    1.02
    sms
    1.01
    just
    0.98
     bleach
    0.97
    Just
    0.97
     everything
    0.97
     correctional
    0.96
    Activations Density 0.004%

    No Known Activations