© 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. 118227
    Prev
    Next
    INDEX
    Explanations

    mathematical fractions `\frac` `{`

    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
    izamos
    -0.86
     DIN
    -0.85
     presidenta
    -0.80
     addSubview
    -0.77
     företag
    -0.76
    ility
    -0.76
     gea
    -0.74
    ཥ
    -0.74
     CURRENT
    -0.74
     ล
    -0.73
    POSITIVE LOGITS
     allows
    0.87
     one
    0.84
     encompasses
    0.81
     received
    0.80
     severely
    0.78
     there
    0.77
    inverno
    0.75
     eliminates
    0.74
     embodies
    0.73
     with
    0.73
    Activations Density 0.019%

    No Known Activations