© 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. 14981
    Prev
    Next
    INDEX
    Explanations

    aim for a goal

    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
    ात
    2.97
     съм
    2.84
    ा
    2.68
     estés
    2.64
     товара
    2.63
    וק
    2.63
    اً
    2.63
     tomada
    2.62
    ا
    2.58
    もの
    2.57
    POSITIVE LOGITS
    م
    4.54
    м
    4.45
    शेद
    4.07
    مم
    3.45
    ्युनिकेशन
    3.28
    ั้ย
    3.25
    ming
    3.23
    ्युनिटी
    3.14
    gekehrt
    3.13
    स्तिष्क
    3.09
    Activations Density 1.483%

    No Known Activations