© 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. 10-GEMMASCOPE-RES-131K
    7. 128062
    Prev
    Next
    INDEX
    Explanations

    alkene or other chemical suffixes

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

    chemical compounds with names ending in "ene".

    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
    ?”
    -2.63
     that
    -2.41
    牐
    -2.39
     become
    -2.28
    毉
    -2.27
    㐂
    -2.25
    肫
    -2.20
    tt
    -2.19
    炻
    -2.16
    鴣
    -2.14
    POSITIVE LOGITS
     "
    2.83
    AutoresizingMask
    2.64
     Meilleures
    2.39
    刧
    2.20
     Réponses
    2.14
     gouvernement
    2.14
    着她
    2.13
    嫆
    2.13
     ſever
    2.13
    ции
    2.13
    Activations Density 0.012%

    No Known Activations