© 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. 15471
    Prev
    Next
    INDEX
    Explanations

    lifting things up

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

    The neuron strongly activates on occurrences of the substring “lift” (in any form such as lift, lifts, lifting).

    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
    0
    -2.81
     tetapi
    -2.45
    il
    -2.39
     But
    -2.38
     notwendigen
    -2.34
    葑
    -2.31
     Except
    -2.30
     nhưng
    -2.20
     reveals
    -2.17
    ↵↵
    -2.16
    POSITIVE LOGITS
     sarcasm
    2.73
     bús
    2.64
    身边的
    2.59
    ꦁ
    2.58
    ﻒ
    2.56
    ’
    2.52
     ་
    2.48
    ’，
    2.33
    救命
    2.27
    汌
    2.27
    Activations Density 0.010%

    No Known Activations