© 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. 69992
    Prev
    Next
    INDEX
    Explanations

    prefixed definitions and keywords

    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
    隐私
    -0.77
     contr
    -0.77
    CAV
    -0.75
    чит
    -0.74
    Симпто
    -0.73
    kops
    -0.70
     carnival
    -0.69
     Contr
    -0.68
     whiskers
    -0.68
    mão
    -0.67
    POSITIVE LOGITS
     guiding
    1.18
     astro
    1.09
     Astro
    0.98
    guided
    0.90
     guided
    0.89
    ahashi
    0.87
    ガイド
    0.85
    astro
    0.85
     Guiding
    0.84
     trailed
    0.83
    Activations Density 0.012%

    No Known Activations