© 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. 45505
    Prev
    Next
    INDEX
    Explanations

    or; as

    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
     spécialement
    -0.94
    |.
    -0.89
     dando
    -0.85
    shang
    -0.81
     Drittel
    -0.80
    还挺
    -0.80
    ClCompile
    -0.79
     見える
    -0.79
     reprez
    -0.79
     limpeza
    -0.79
    POSITIVE LOGITS
     or
    0.94
     in
    0.84
    ե
    0.80
    Variants
    0.77
    setPos
    0.74
     mukana
    0.73
     kuiten
    0.73
    場合には
    0.72
    getHeaders
    0.72
     spelled
    0.71
    Activations Density 0.138%

    No Known Activations