© 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. 119668
    Prev
    Next
    INDEX
    Explanations

    addition and multiplication

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

    mathematical operations, particularly addition, subtraction, and multiplication.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     ‘’
    -1.36
     viewDid
    -1.35
    ╭
    -1.34
    ’
    -1.30
     –
    -1.30
    🔴
    -1.29
    лон
    -1.27
     дальней
    -1.27
    hibits
    -1.24
     ',',
    -1.24
    POSITIVE LOGITS
     beeinf
    1.76
     acogedor
    1.59
     our
    1.59
     Когда
    1.53
     kleinen
    1.51
     between
    1.50
     בין
    1.46
     beschleun
    1.45
     Однако
    1.44
     bestehenden
    1.39
    Activations Density 0.043%

    No Known Activations