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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 642
    Prev
    Next
    INDEX
    Explanations

    list separator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    它
    1.07
    s
    1.06
    ﻉ
    1.02
     awaits
    1.02
     directs
    1.01
     temer
    0.98
     procure
    0.96
     suspects
    0.95
    এই
    0.93
    蝣
    0.93
    POSITIVE LOGITS
    że
    1.39
    িং
    1.16
    ekkür
    1.10
    zelfde
    1.10
    engined
    1.10
    om
    1.09
    e
    1.09
    ap
    1.09
    ovým
    1.05
    age
    1.05
    Activations Density 0.276%

    No Known Activations