Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8229
    Prev
    Next
    INDEX
    Explanations

    skin care routine, body shape

    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_262k_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
    т
    1.73
    ون
    1.51
    ます
    1.46
    ्स
    1.45
    ्व
    1.41
    s
    1.38
    ের
    1.35
    ों
    1.35
    ますが
    1.34
    sd
    1.34
    POSITIVE LOGITS
    てください
    1.41
    ر
    1.38
     đựng
    1.33
     garantiza
    1.31
     refuer
    1.31
    ם
    1.30
     rodzaj
    1.29
     তবে
    1.28
     состояния
    1.27
     лица
    1.27
    Activations Density 0.002%

    No Known Activations