© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65632
    Prev
    Next
    INDEX
    Explanations

    keywords ending lines

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

    The neuron is triggered by integer numeric constants (literal numbers) in code.

    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
     to
    -1.41
    katakan
    -1.34
    ッタリ
    -1.20
     from
    -1.11
    malte
    -1.10
     bilhões
    -1.09
    の為
    -1.05
     Projektu
    -1.04
    心底
    -1.04
    方がいい
    -1.04
    POSITIVE LOGITS
    例文
    1.18
    êng
    1.10
     camas
    1.09
    quelize
    1.04
     Cymru
    1.03
    そして
    1.02
    lső
    1.02
    战术
    1.02
    ariConfig
    1.02
    ousness
    1.01
    Activations Density 0.000%

    No Known Activations