© 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. 14470
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    This neuron detects long, multi-syllabic technical or scientific content words (e.g., Latin-derived stems).

    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
    Celltype
    0.34
    valuer
    0.33
    Descripcion
    0.33
     Agricult
    0.33
    ihuahua
    0.33
    诮
    0.33
    Genero
    0.32
    uvad
    0.32
    新型コロナ
    0.32
    Month
    0.31
    POSITIVE LOGITS
     framework
    0.38
     frameworks
    0.38
     such
    0.33
     şi
    0.32
     subsystem
    0.32
    সমূ
    0.32
     sources
    0.32
     및
    0.32
     pursuit
    0.32
    および
    0.32
    Activations Density 0.000%

    No Known Activations