© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 2064
    Prev
    Next
    INDEX
    Explanations

    deliver results

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

    The neuron strongly fires on occurrences of the verb "deliver."

    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_24_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
    t
    1.66
    n
    1.20
    tio
    1.07
    tional
    1.06
    ts
    1.01
    tym
    0.99
    tedir
    0.98
    s
    0.96
    ta
    0.88
    től
    0.86
    POSITIVE LOGITS
    𝗘
    1.13
     inoxidable
    1.09
    ،
    1.05
    =\{
    1.03
    ो
    1.02
    ，
    1.02
    ﻟ
    1.01
    𝖽
    1.00
    ፣
    1.00
    hasil
    0.97
    Activations Density 0.012%

    No Known Activations