© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13673
    Prev
    Next
    INDEX
    Explanations

    anabolic steroids

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

    This neuron activates on words related to steroids and steroid-related compounds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the presence of the substring “steroid” (e.g. in “steroid,” “anabolic steroids,” “steroidogenic,” etc.)

    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
    u
    -2.61
    t
    -2.52
    ⦊
    -2.41
    \
    -2.31
    (
    -2.25
    O
    -2.16
    1
    -2.14
    d
    -2.09
     perched
    -2.09
     tossed
    -2.09
    POSITIVE LOGITS
    姈
    2.63
    沺
    2.59
     speziellen
    2.47
     tocó
    2.45
    饹
    2.42
     новым
    2.41
     vistas
    2.36
    蛲
    2.34
    蘼
    2.33
    CÓMO
    2.30
    Activations Density 0.005%

    No Known Activations