© 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. 6951
    Prev
    Next
    INDEX
    Explanations

    special characters and markup

    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
     and
    -1.05
     or
    -0.96
     with
    -0.93
     in
    -0.93
     on
    -0.89
     since
    -0.86
     of
    -0.86
     for
    -0.84
    TRIBUN
    -0.80
     by
    -0.78
    POSITIVE LOGITS
     Gerrit
    0.88
    ⸮
    0.87
     доме
    0.83
    ↼
    0.82
     aquellas
    0.81
    ጎ
    0.81
     refroid
    0.79
     diminishes
    0.79
     plung
    0.79
     Holds
    0.79
    Activations Density 0.008%

    No Known Activations