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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 11263
    Prev
    Next
    INDEX
    Explanations

    chemical formulas with variables

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

    chemical formulas with subscripts and numerical indices.

    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
     is
    -1.93
     to
    -1.73
     realities
    -1.41
     divertidas
    -1.33
     if
    -1.33
     when
    -1.31
     gainera
    -1.30
    ICIOS
    -1.27
     may
    -1.25
    𓆟
    -1.23
    POSITIVE LOGITS
    <bos>
    1.51
    댁
    1.45
     אחרים
    1.45
    zzá
    1.34
    Де
    1.33
    PLICIT
    1.31
    સ
    1.30
     Tôi
    1.27
     पानी
    1.26
     trám
    1.25
    Activations Density 0.029%

    No Known Activations