© 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. 22-GEMMASCOPE-RES-131K
    7. 95661
    Prev
    Next
    INDEX
    Explanations

    suitability and context

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

    The neuron detects occurrences of the word “appropriate,” especially when used to ask whether something is appropriate for or to do.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    蹰
    -2.53
    archiwizowane
    -2.48
    ’，
    -2.47
    ⎚
    -2.42
    冋
    -2.41
     The
    -2.34
    ✇
    -2.30
    鹪
    -2.30
    🫱
    -2.27
    蠖
    -2.27
    POSITIVE LOGITS
    鋮
    2.42
    Some
    2.41
    Several
    2.33
    ஂ
    2.33
    瑧
    2.30
    Although
    2.28
    n
    2.27
     That
    2.25
    酲
    2.23
     enticing
    2.22
    Activations Density 0.008%

    No Known Activations