© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    discussion of life and living

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

    text that expresses purpose or intention, often triggering on phrases starting with "to" followed by a verb.

    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
    really
    -1.26
     magnifique
    -1.07
    actually
    -1.05
    truly
    -1.03
     qualifi
    -1.00
     Þ
    -0.99
    declared
    -0.98
     trés
    -0.98
    seems
    -0.98
    感觉到
    -0.98
    POSITIVE LOGITS
     this
    1.68
     website
    1.59
     comments
    1.54
     discussion
    1.49
     analysis
    1.45
     data
    1.44
     debate
    1.41
     article
    1.36
     comment
    1.34
     previous
    1.30
    Activations Density 0.570%

    No Known Activations