© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63754
    Prev
    Next
    INDEX
    Explanations

    drug names and legal terms

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

    text associated with spam, pornography, or other web content that has formatting characteristic of automatically generated content.

    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
     dandy
    -0.94
     waisted
    -0.89
     TOT
    -0.88
     HIGHER
    -0.86
     TERR
    -0.85
    setopt
    -0.84
    泞
    -0.83
    верь
    -0.81
     Assess
    -0.81
     hedon
    -0.80
    POSITIVE LOGITS
     how
    1.77
     what
    1.60
     which
    1.20
     when
    1.11
     why
    1.08
     where
    1.03
     who
    0.97
     last
    0.88
     easy
    0.81
     necessary
    0.80
    Activations Density 0.003%

    No Known Activations