© 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. 50407
    Prev
    Next
    INDEX
    Explanations

    patent numbers, legal citations

    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
    ourage
    -0.77
     Prieto
    -0.77
     Dames
    -0.75
    月号
    -0.74
     javax
    -0.74
     Seven
    -0.73
    ressen
    -0.72
     terceiro
    -0.72
     avven
    -0.71
     HFILL
    -0.71
    POSITIVE LOGITS
    视图
    0.71
     nueve
    0.67
     качестве
    0.67
    ❾
    0.66
     robber
    0.66
    Converting
    0.65
    Cloudy
    0.65
    9
    0.65
     mely
    0.65
    Kaya
    0.64
    Activations Density 0.047%

    No Known Activations