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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 47475
    Prev
    Next
    INDEX
    Explanations

    Checking in

    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_65k_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
    ifax
    1.16
    ؘ
    1.12
    可以看出
    1.07
    				
    1.05
    ultaneous
    1.05
     '.';
    1.05
    ")));
    1.05
    ेटर
    1.04
           
    1.03
    elihat
    1.03
    POSITIVE LOGITS
    ر
    1.44
     puk
    1.29
     কাগ
    1.20
     नवा
    1.13
    ع
    1.13
     não
    1.13
     ya
    1.13
     puh
    1.12
     sint
    1.11
     adequado
    1.11
    Activations Density 0.004%

    No Known Activations