© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3122
    Prev
    Next
    INDEX
    Explanations

    escalate conflict

    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
    م
    1.66
     pert
    1.65
    裸
    1.59
     голо
    1.58
    ౖ
    1.57
    affe
    1.54
     novel
    1.49
    dac
    1.49
    TRA
    1.48
     nus
    1.47
    POSITIVE LOGITS
     kPa
    2.07
    𝕜
    2.01
     angiogenesis
    1.99
     embeddings
    1.99
     encontr
    1.98
    லாத
    1.96
    kPa
    1.94
     गिरफ्त
    1.93
    ADOW
    1.93
    Executive
    1.92
    Activations Density 0.027%

    No Known Activations