© 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. 104638
    Prev
    Next
    INDEX
    Explanations

    timestamps and code changes

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

    The neuron is tuned to pick out ordinary English words in running text (and thus stays silent on code‐diff syntax).

    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
     other
    -1.80
     their
    -1.60
    薦
    -1.42
     various
    -1.41
     many
    -1.36
    甕
    -1.36
    その
    -1.29
     always
    -1.28
    砥
    -1.25
    を
    -1.24
    POSITIVE LOGITS
    ↵
    1.57
    '
    1.55
    為に
    1.54
    いっ
    1.37
    ビックリ
    1.27
    一切都
    1.21
    事は
    1.20
    凄く
    1.20
    マジで
    1.20
    事が
    1.19
    Activations Density 0.001%

    No Known Activations