© 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. 10290
    Prev
    Next
    INDEX
    Explanations

    above sea

    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
     devant
    0.96
     câte
    0.95
    wohner
    0.94
    ⃣
    0.94
     nuit
    0.92
    ☛
    0.91
     tend
    0.91
     applause
    0.89
    '_
    0.89
     tật
    0.88
    POSITIVE LOGITS
    сред
    0.90
    Lew
    0.88
    마
    0.87
    сход
    0.87
     Bored
    0.86
    Grey
    0.85
    석
    0.85
    у
    0.84
    치가
    0.84
    라이
    0.84
    Activations Density 0.023%

    No Known Activations