© 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. 89
    Prev
    Next
    INDEX
    Explanations

    the neuron responds strongly to future‐tense modal verbs (especially “will” and similar predictive forms).

    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
     thẻ
    0.34
     kepada
    0.34
                        
    0.33
     ${
    0.33
     topography
    0.33
     androidx
    0.32
     région
    0.32
     kutoka
    0.31
    -
    0.31
     '@
    0.31
    POSITIVE LOGITS
    ن
    0.60
    n
    0.49
    ر
    0.47
    b
    0.45
    ع
    0.43
     দেরী
    0.42
    ل
    0.42
    l
    0.41
    t
    0.40
     प्रूव
    0.40
    Activations Density 0.000%

    No Known Activations