© 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. 3458
    Prev
    Next
    INDEX
    Explanations

    wikipedia links

    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
    salon
    1.71
    न
    1.47
    sports
    1.34
    sal
    1.26
     Honours
    1.26
     honoured
    1.25
    dance
    1.20
    óż
    1.20
     combustion
    1.18
    solid
    1.18
    POSITIVE LOGITS
    𝐑
    1.31
    Бо
    1.27
     sns
    1.26
    𝐱
    1.24
    𝘣
    1.23
     подход
    1.23
    𝑯
    1.22
    な
    1.22
    у
    1.21
    jší
    1.20
    Activations Density 0.006%

    No Known Activations