© 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. 34-GEMMASCOPE-RES-131K
    7. 47511
    Prev
    Next
    INDEX
    Explanations

    reacting or reaction

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

    words related to reactions or responding to stimuli, particularly the word "reaction" and its variations.

    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_34/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
    ead
    -0.88
    enerbah
    -0.88
    𝔡
    -0.85
    rigated
    -0.85
    ہ
    -0.84
    nicity
    -0.81
    Repeti
    -0.81
    vejte
    -0.80
     Erkrank
    -0.79
     bền
    -0.79
    POSITIVE LOGITS
     Reaction
    1.66
     reacts
    1.55
    reaction
    1.45
     react
    1.39
     React
    1.39
     reaction
    1.38
     reactions
    1.35
    react
    1.33
     Reactions
    1.28
     reacted
    1.27
    Activations Density 0.027%

    No Known Activations