© 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. 13440
    Prev
    Next
    INDEX
    Explanations

    consecutive numbers or sequences

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

    The neuron flags salient content words—i.e. uncommon, information‐bearing nouns and verbs—rather than 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
    o
    1.05
    i
    0.95
    e
    0.93
    tf
    0.80
     アンティーク
    0.78
    ו
    0.78
    iap
    0.77
    ft
    0.76
    ió
    0.74
    lesson
    0.74
    POSITIVE LOGITS
    ное
    0.88
    ското
    0.82
    йдз
    0.81
    𝙽
    0.80
    ных
    0.79
    ленное
    0.79
    ﻜ
    0.77
    граммы
    0.74
     Старки
    0.73
    ны
    0.71
    Activations Density 0.001%

    No Known Activations