© 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. 79982
    Prev
    Next
    INDEX
    Explanations

    height =

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

    The neuron does not activate on any tokens—it effectively matches nothing.

    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
    a
    -3.03
    u
    -2.77
    ↵↵
    -2.77
    犛
    -2.53
     また
    -2.30
    袮
    -2.17
    off
    -2.14
    高达
    -2.09
     When
    -2.06
     ingrained
    -2.05
    POSITIVE LOGITS
    𖧵
    2.70
     \
    2.64
     of
    2.59
    ⃠
    2.50
    媄
    2.45
     You
    2.45
     flere
    2.42
     verhind
    2.39
     erhi
    2.36
    趼
    2.36
    Activations Density 0.013%

    No Known Activations