© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25254
    Prev
    Next
    INDEX
    Explanations

    proper nouns and technical terms

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

    The neuron detects the opening lines of an explanatory or solution sentence (i.e. the start of an answer paragraph).

    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
     ardından
    -0.95
     Informações
    -0.93
    rophi
    -0.91
    不能
    -0.88
     étab
    -0.86
    できれば
    -0.85
    เพื่อ
    -0.83
     Dolby
    -0.82
     certainement
    -0.81
     vacaciones
    -0.81
    POSITIVE LOGITS
     dagegen
    1.38
     hingegen
    1.30
     OTO
    1.04
     наоборот
    1.01
     comparatively
    1.01
     invece
    0.95
     Pelo
    0.95
     problems
    0.94
    そういった
    0.93
     can
    0.92
    Activations Density 0.050%

    No Known Activations