© 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. 34-GEMMASCOPE-RES-131K
    7. 116960
    Prev
    Next
    INDEX
    Explanations

    shader code and declarations

    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
    ہر
    -0.95
     Cinta
    -0.84
     CBSE
    -0.84
     danych
    -0.83
     口罩
    -0.77
    AppCompat
    -0.77
    operations
    -0.76
    coltà
    -0.75
     genutzt
    -0.75
     cytoplasmic
    -0.74
    POSITIVE LOGITS
     vec
    1.08
    vec
    1.07
     gl
    0.93
    gl
    0.91
     Gl
    0.84
    ccccccc
    0.84
     Frag
    0.83
    까
    0.80
    Mori
    0.77
     golpea
    0.76
    Activations Density 0.024%

    No Known Activations