© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 56075
    Prev
    Next
    INDEX
    Explanations

    no change or effect

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

    The neuron is highly sensitive to negation or null‐effect cues—words and phrases (e.g. “no,” “without,” “not”) signaling absence of change or effect.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    somewhat
    -1.34
    potentially
    -1.25
     biraz
    -1.20
     somewhat
    -1.17
     både
    -1.13
    schon
    -1.11
     некото
    -1.09
     parfois
    -1.09
     måske
    -1.09
     菇
    -1.09
    POSITIVE LOGITS
     any
    2.20
     significant
    1.84
     change
    1.50
     obvious
    1.48
     noticeable
    1.45
     differences
    1.39
     detectable
    1.34
     changes
    1.31
     clear
    1.29
     Significant
    1.22
    Activations Density 0.162%

    No Known Activations