© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 253
    Prev
    Next
    INDEX
    Explanations

    security, funding, and negation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    barrels
    1.18
    ie
    1.17
    -(
    1.12
    (!)
    1.12
     oder
    1.10
     weet
    1.08
     wart
    1.07
    вил
    1.07
    videmment
    1.06
    (_
    1.04
    POSITIVE LOGITS
     здійсню
    1.69
     高校
    1.66
     文件
    1.60
    ﻷ
    1.59
     函数
    1.58
     校
    1.56
     首
    1.55
     理
    1.54
     刺繍
    1.52
    ková
    1.51
    Activations Density 0.020%

    No Known Activations