© 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. 24-GEMMASCOPE-2-RES-16K
    4. 13763
    Prev
    Next
    INDEX
    Explanations

    crossing into, fall outside

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

    The neuron fires on dynamic “movement” words—verbs and prepositions that describe motion or transition (e.g. into, fall, start, rush, fill).

    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
    s
    1.07
    ing
    0.84
    inizio
    0.84
    ot
    0.83
    sr
    0.83
    sns
    0.82
    સ
    0.81
    The
    0.80
    ouverture
    0.80
    ка
    0.79
    POSITIVE LOGITS
     oblivion
    1.03
     skladu
    0.93
    窘
    0.92
    撳
    0.92
     kategor
    0.91
     giấc
    0.90
     kepercayaan
    0.89
    ﻟ
    0.88
     обычно
    0.88
     considerados
    0.87
    Activations Density 0.817%

    No Known Activations