© 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. 3962
    Prev
    Next
    INDEX
    Explanations

    almost followed by intensifiers

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

    This neuron detects adverbial approximators (words like “almost” and “nearly”).

    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
    твы
    0.89
    몫
    0.87
    على
    0.84
    Спо
    0.78
    можно
    0.75
    Очень
    0.74
    ks
    0.73
    私募基金
    0.72
    تو
    0.72
    憾
    0.72
    POSITIVE LOGITS
    nými
    0.83
     importantly
    0.80
    ran
    0.79
     aussitôt
    0.79
    .")
    0.78
    ре
    0.76
    ————————
    0.74
    на
    0.74
    ان
    0.71
    .\
    0.70
    Activations Density 0.020%

    No Known Activations