© 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. 111128
    Prev
    Next
    INDEX
    Explanations

    extreme negative adjectives

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

    The neuron fires on strong negative descriptors or modifiers (often broken into subword pieces like “prohib-…-itive,” “impos-…-ible,” “back-breaking,” “unbearable”) that signal extreme difficulty, cost, or severity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     vyrá
    -1.56
    notre
    -1.56
    bruh
    -1.50
     domestiques
    -1.50
     vios
    -1.47
     doraemon
    -1.47
     coreana
    -1.45
    assume
    -1.45
     than
    -1.45
     naruto
    -1.44
    POSITIVE LOGITS
    sig
    1.49
    mistic
    1.48
    ка
    1.48
    ви
    1.47
    .”
    1.45
    har
    1.45
    </u>
    1.43
    ти
    1.43
     E
    1.42
    取り付け
    1.41
    Activations Density 0.026%

    No Known Activations