© 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. 33464
    Prev
    Next
    INDEX
    Explanations

    introduction to consequence or explanation

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

    This neuron strongly activates on the word “reason” when it occurs as an explanatory discourse marker (e.g. “for this reason,” “for that reason,” “for these reasons”).

    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
    ústria
    -1.51
     what
    -1.36
    𝔃
    -1.25
    ၞ
    -1.25
     haphazard
    -1.25
    閂
    -1.20
     như
    -1.19
     nahezu
    -1.16
    tiert
    -1.16
     allmäh
    -1.16
    POSITIVE LOGITS
     alcuni
    1.33
    many
    1.31
    some
    1.29
    0
    1.27
    even
    1.26
     we
    1.26
     многих
    1.24
     why
    1.23
    3
    1.22
    it
    1.21
    Activations Density 0.009%

    No Known Activations