© 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
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14339
    Prev
    Next
    INDEX
    Explanations

    employee terms and HR contexts

    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
    ඍ
    3.10
    𝑙
    3.02
    quefois
    2.94
    ﻞ
    2.89
    HideFlags
    2.76
    hdad
    2.71
    AnalyzeAction
    2.69
    唰
    2.68
    जैसा
    2.65
     sodass
    2.64
    POSITIVE LOGITS
    si
    2.22
    ς
    2.20
    slan
    2.09
    se
    2.09
    sen
    1.99
    ship
    1.98
    sit
    1.95
    lan
    1.95
    leng
    1.94
    pen
    1.94
    Activations Density 0.041%

    No Known Activations