© 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. 98461
    Prev
    Next
    INDEX
    Explanations

    code blocks or structured data

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

    The neuron is triggered by numeric measurement or dimension specifications (numbers with hyphens, “x”, “@”, units or quotes).

    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
     information
    -1.28
     mostly
    -1.24
     after
    -1.24
     mainly
    -1.16
     trying
    -1.14
     primarily
    -1.14
     almost
    -1.13
     from
    -1.09
     or
    -1.06
     focusing
    -1.02
    POSITIVE LOGITS
    の使用
    1.23
     löytyy
    1.14
     dringend
    1.14
     bawat
    1.13
     necesario
    1.07
     overarching
    1.06
     käyttö
    1.04
     ouvido
    1.02
     ausreichend
    1.02
     biedt
    1.01
    Activations Density 0.011%

    No Known Activations