© 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. 86883
    Prev
    Next
    INDEX
    Explanations

    short unsigned int WORD sizes

    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
     long
    -0.89
    PRESIDENT
    -0.83
     millions
    -0.82
     million
    -0.76
     justru
    -0.69
     ulong
    -0.67
     milioni
    -0.67
     just
    -0.66
     mice
    -0.66
     Long
    -0.65
    POSITIVE LOGITS
     htons
    1.58
    xFFFF
    1.39
    short
    1.31
     short
    1.30
     ushort
    1.27
    Short
    1.25
    xffff
    1.24
    ushort
    1.16
     Short
    1.12
    WORD
    1.02
    Activations Density 0.022%

    No Known Activations