© 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. 22-GEMMASCOPE-RES-131K
    4. 74003
    Prev
    Next
    INDEX
    Explanations

    CSS units (px, em)

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

    The neuron detects standalone numeric constants in CSS property values (especially the three offset values in box-shadow declarations).

    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
    鰨
    -1.17
    それは
    -1.16
     all
    -1.13
    CLUYE
    -1.10
     GALERÍA
    -1.06
     bedankt
    -1.06
     Heilige
    -1.04
    maları
    -1.03
    螄
    -1.03
    unjungi
    -1.02
    POSITIVE LOGITS
    M
    1.20
     organisiert
    1.19
    うま
    1.12
     pengertian
    1.09
    C
    1.08
    P
    1.08
    した後
    1.07
    的就
    1.07
    T
    1.07
    am
    1.05
    Activations Density 0.002%

    No Known Activations