© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10549
    Prev
    Next
    INDEX
    Explanations

    freshness

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

    The neuron fires on adjectives and adverbs signaling freshness or newness (e.g. "fresh," "freshly," "newly").

    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
    রত
    0.64
     наслед
    0.62
    irnya
    0.61
    tio
    0.59
    apunov
    0.58
    檯
    0.57
    cie
    0.57
     bâtiments
    0.57
    товой
    0.56
    ු
    0.56
    POSITIVE LOGITS
    Fresh
    1.69
     Fresh
    1.67
     fresh
    1.63
     FRESH
    1.55
     freshness
    1.49
    fresh
    1.45
     freshen
    1.33
     freshest
    1.33
     fresher
    1.32
     Fres
    1.27
    Activations Density 0.116%

    No Known Activations