© 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. 6879
    Prev
    Next
    INDEX
    Explanations

    excluding before activation

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

    The neuron consistently activates on standalone numeric values (e.g. quantities, prices, statistics).

    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
     অর্থের
    0.70
     financially
    0.66
    financ
    0.66
     finanzi
    0.66
    財
    0.65
     finances
    0.61
    大手
    0.60
     টাকার
    0.59
    zeigt
    0.59
    💵
    0.59
    POSITIVE LOGITS
     allowances
    1.20
     excluding
    1.19
     excludes
    1.11
     subtracting
    1.10
     Subtract
    1.10
     allowance
    1.09
     exclude
    1.08
     subtract
    1.07
     bonuses
    1.06
     excluded
    1.04
    Activations Density 0.463%

    No Known Activations