© 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. 9510
    Prev
    Next
    INDEX
    Explanations

    balance tax

    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
    ח
    1.40
    क
    1.32
    snd
    1.28
    خ
    1.23
    ג
    1.21
     uur
    1.18
    वारा
    1.17
    ights
    1.13
    Цент
    1.13
    і
    1.13
    POSITIVE LOGITS
     třeba
    1.28
     sitä
    1.15
     sería
    1.14
     cú
    1.06
     bigger
    1.00
     comedor
    1.00
     když
    0.99
     nějak
    0.96
     başka
    0.95
     hük
    0.94
    Activations Density 0.002%

    No Known Activations