© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4967
    Prev
    Next
    INDEX
    Explanations

    level rise

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

    The neuron flags content‐bearing, “meaningful” words (nouns, verbs, adjectives) and stays silent on common function words.

    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
    1.02
    𝘽
    0.98
     fabricants
    0.91
    𝘾
    0.90
    вної
    0.84
    投注
    0.84
    𝙨
    0.84
    𝘿
    0.84
    𝙛
    0.84
    euros
    0.83
    POSITIVE LOGITS
     banding
    0.80
     stacks
    0.76
     Commission
    0.71
     ideal
    0.71
     ساز
    0.70
     কাছে
    0.68
    banding
    0.66
     Generator
    0.66
    ↵↵↵
    0.65
     ends
    0.65
    Activations Density 0.000%

    No Known Activations