© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36387
    Prev
    Next
    INDEX
    Explanations

    just starting

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

    The neuron fires on instances of “just” plus a following action (e.g. “just works,” “just starting,” “just have to”), i.e. constructions that convey simplicity or ease.

    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
    même
    -1.35
    珰
    -1.33
     большинстве
    -1.32
    zapatos
    -1.30
    ﺶ
    -1.28
    躂
    -1.28
    峮
    -1.25
    ݮ
    -1.24
    iramente
    -1.24
    </h3>
    -1.24
    POSITIVE LOGITS
    and
    1.39
    '
    1.37
     got
    1.23
     gets
    1.19
     kids
    1.19
    I
    1.18
    end
    1.16
    </b>
    1.15
     started
    1.11
    y
    1.11
    Activations Density 0.064%

    No Known Activations