© 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. 23692
    Prev
    Next
    INDEX
    Explanations

    medical/scientific references

    np_acts-logits-general · gemini-2.5-flash-lite

    programming code documentation and comments, particularly in annotation formats like @var, //, and /* */.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     भर
    -0.84
    sei
    -0.73
     eugen
    -0.72
     rebirth
    -0.69
     fili
    -0.68
     voraus
    -0.67
     Daryl
    -0.67
    满脸
    -0.67
    衛門
    -0.67
    mund
    -0.67
    POSITIVE LOGITS
     Hamm
    0.75
    ərb
    0.73
     miej
    0.72
    avent
    0.69
     Fonte
    0.69
     złota
    0.69
    gulls
    0.69
    Ⅺ
    0.67
    Demi
    0.67
    mein
    0.66
    Activations Density 0.040%

    No Known Activations