© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 15152
    Prev
    Next
    INDEX
    Explanations

    laws of physics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     당시
    1.07
     대한민국
    1.06
     răz
    1.05
     précéd
    1.05
     한국
    1.03
     préparations
    1.02
     정치
    1.01
     (**
    1.00
     производстве
    1.00
     jì
    0.99
    POSITIVE LOGITS
    ok
    1.05
    ap
    0.86
    R
    0.79
    po
    0.77
    1
    0.76
    ol
    0.76
    ymptotic
    0.75
    phenyl
    0.75
    avg
    0.74
    B
    0.73
    Activations Density 0.001%

    No Known Activations