© 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. 38427
    Prev
    Next
    INDEX
    Explanations

    bit rates and encoding

    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
    дна
    -0.74
     Hanford
    -0.73
    Wes
    -0.73
     โล
    -0.71
     litro
    -0.69
    СТВО
    -0.68
     розмі
    -0.68
    Извест
    -0.67
    ப
    -0.67
     Harm
    -0.66
    POSITIVE LOGITS
     bit
    1.81
     bits
    1.63
     Bit
    1.52
    Bit
    1.45
    bit
    1.45
    bits
    1.34
     Bits
    1.33
     BIT
    1.27
    Bits
    1.26
    BIT
    1.20
    Activations Density 0.062%

    No Known Activations