© 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. 68095
    Prev
    Next
    INDEX
    Explanations

    the + noun explaining a fact or reason

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

    The neuron fires on abstract, evaluative or quantitative concept words (like “importance,” “difficulties,” “magnitude,” etc.), especially when they appear in question or explanatory contexts.

    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
     سایر
    -1.26
    その
    -1.24
    ных
    -1.20
    もちろん
    -1.19
    拇
    -1.18
    🔊
    -1.16
     =-\
    -1.16
     deler
    -1.13
    はその
    -1.12
    poort
    -1.08
    POSITIVE LOGITS
    えっ
    1.72
    のご紹介
    1.67
    明日は
    1.63
    メルカリ
    1.61
    感じで
    1.57
    定価
    1.55
    本日の
    1.55
    おそ
    1.52
    ごめん
    1.51
    ではでは
    1.43
    Activations Density 0.081%

    No Known Activations