© 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. 93133
    Prev
    Next
    INDEX
    Explanations

    from __future__ import

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

    This neuron detects Python’s “from __future__ import …” statements.

    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
     lihat
    -1.38
    しちゃ
    -1.33
     its
    -1.33
     their
    -1.30
     comprometido
    -1.25
    鍘
    -1.24
     sehr
    -1.24
    utusan
    -1.23
     provocar
    -1.23
     joyas
    -1.23
    POSITIVE LOGITS
    ,
    1.63
    !
    1.57
    o
    1.48
    i
    1.45
    e
    1.44
    1.44
    </u>
    1.42
    v
    1.41
    m
    1.40
    w
    1.39
    Activations Density 0.007%
    No Known Activations