© 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. 10-GEMMASCOPE-RES-131K
    7. 127969
    Prev
    Next
    INDEX
    Explanations

    Past states or conditions

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

    The neuron consistently activates on the adverb “always” (and similar high‐frequency/time‐indicating adverbs).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     the
    -1.71
    ícias
    -1.43
    倶楽部
    -1.39
     "
    -1.34
    </strong>
    -1.31
     their
    -1.26
    </em>
    -1.24
    >
    -1.20
    一方面
    -1.18
    "--
    -1.17
    POSITIVE LOGITS
     bahkan
    1.55
     内部
    1.30
    頭皮
    1.25
     加载
    1.23
    𞤤
    1.22
     serupa
    1.21
     ஒரு
    1.17
     berkualitas
    1.17
    CDT
    1.17
    timmung
    1.16
    Activations Density 0.019%

    No Known Activations