© 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. 12108
    Prev
    Next
    INDEX
    Explanations

    code and technical terms

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

    multiplication operators or variable assignments in mathematical and programming contexts.

    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
    specifically
    -1.65
    certainly
    -1.61
     seks
    -1.59
    簌
    -1.57
     spontan
    -1.55
     fluide
    -1.52
     ruine
    -1.51
    wonderful
    -1.50
    桫
    -1.48
    -1.48
    POSITIVE LOGITS
     on
    1.86
    These
    1.60
    Since
    1.58
    With
    1.55
    During
    1.52
     give
    1.51
    Because
    1.46
    When
    1.45
     are
    1.45
     Because
    1.45
    Activations Density 0.063%

    No Known Activations