© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4265
    Prev
    Next
    INDEX
    Explanations

    after prepositions and conjunctions

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

    The neuron flags high-frequency function words and transitional/discourse tokens (e.g. “even,” “there,” “follow,” and commas).

    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
    ן
    0.92
    פר
    0.88
    ursed
    0.85
    Screw
    0.84
    SL
    0.82
    ب
    0.82
    ע
    0.79
    practice
    0.78
    ם
    0.77
    surprise
    0.77
    POSITIVE LOGITS
     teken
    0.89
     immunization
    0.86
    тности
    0.86
     leukaemia
    0.85
    твы
    0.83
     übertr
    0.82
    тивов
    0.82
     gebru
    0.81
     tej
    0.81
     entrar
    0.80
    Activations Density 0.000%

    No Known Activations