© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99140
    Prev
    Next
    INDEX
    Explanations

    scientific studies and experiments

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

    terms referring to scientific experiments or research studies and their duration or completion.

    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
     before
    -1.84
     and
    -1.82
     for
    -1.82
     from
    -1.82
     with
    -1.75
     that
    -1.68
     in
    -1.66
     already
    -1.64
     of
    -1.62
     after
    -1.59
    POSITIVE LOGITS
     sentra
    1.49
    豋
    1.41
    السلام
    1.40
     avancer
    1.38
    Instead
    1.36
     épu
    1.35
     tuta
    1.34
     réfrigérateur
    1.31
     Istri
    1.30
    ㌧
    1.30
    Activations Density 0.069%

    No Known Activations