© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6145
    Prev
    Next
    INDEX
    Explanations

    legal definitions, activate, principles

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

    The neuron primarily responds to decimal number tokens (floating-point numeric values).

    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
    String
    0.77
    the
    0.76
    AR
    0.75
    AS
    0.71
    a
    0.70
    Ordered
    0.66
    t
    0.66
    Invalid
    0.66
    }`);
    0.66
    ER
    0.64
    POSITIVE LOGITS
     softwares
    0.86
     appetizers
    0.79
    सीना
    0.75
     engagements
    0.73
     marketplaces
    0.73
    যত
    0.72
     grooves
    0.72
    abhavo
    0.72
     paradigms
    0.72
     wares
    0.71
    Activations Density 0.049%

    No Known Activations