© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 178
    Prev
    Next
    INDEX
    Explanations

    want to / like to

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

    The neuron fires on numeric tokens, i.e. occurrences of numbers or quantities.

    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
    '
    0.30
    }
    0.29
    )
    0.27
    。
    0.27
    ×
    0.27
    -
    0.27
     bulunduğu
    0.26
     }
    0.26
     ×
    0.26
     etc
    0.25
    POSITIVE LOGITS
     desperately
    0.55
     reassurance
    0.52
     aiuto
    0.48
     assurances
    0.45
     clarification
    0.45
     help
    0.42
     reimbursement
    0.41
     möglichst
    0.41
     clarifications
    0.41
     rohkem
    0.41
    Activations Density 0.594%

    No Known Activations