© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60665
    Prev
    Next
    INDEX
    Explanations

    shortening or bypassing

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

    words related to shortening, abbreviating or limiting something.

    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_10/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
     him
    -2.25
     —
    -2.06
    "
    -1.99
     údaj
    -1.97
     But
    -1.96
     organize
    -1.94
     הוא
    -1.93
    𝗣
    -1.91
    都想
    -1.91
     vlast
    -1.90
    POSITIVE LOGITS
    ↵
    2.66
     curtail
    2.58
    絰
    2.48
     für
    2.47
    Только
    2.44
    _{
    2.44
     для
    2.41
    h
    2.41
     برای
    2.38
    e
    2.38
    Activations Density 0.003%

    No Known Activations