© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 854
    Prev
    Next
    INDEX
    Explanations

    margin and padding

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

    This neuron activates on numeric tokens (digits and measurement values) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    )](
    0.52
     compartments
    0.49
     symbolically
    0.46
     vibe
    0.46
     obrigado
    0.46
     emoji
    0.45
     crossbody
    0.45
     kleur
    0.45
    ][$
    0.44
     emojis
    0.44
    POSITIVE LOGITS
    tabPadding
    0.55
    marginTop
    0.52
     紙
    0.52
     সর্বো
    0.52
    茟
    0.49
    દર
    0.47
    เก
    0.46
    bigskip
    0.46
    PAPER
    0.46
     कर्फ
    0.46
    Activations Density 0.004%

    No Known Activations