© 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. 16064
    Prev
    Next
    INDEX
    Explanations

    directory paths

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

    This neuron detects the first meaningful content word at the start of a new segment or heading.

    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
    http
    0.70
    seekBar
    0.61
     ihe
    0.61
    television
    0.60
    Municipio
    0.59
     тощо
    0.59
    ();
    0.58
    the
    0.58
     необхідно
    0.58
    😟
    0.58
    POSITIVE LOGITS
     outlier
    0.69
     mythical
    0.68
     GWAS
    0.66
     outliers
    0.65
     IVF
    0.65
     Macbook
    0.64
     qubits
    0.63
     kebab
    0.63
     Rohingya
    0.63
     LGBTQ
    0.63
    Activations Density 0.367%

    No Known Activations