© 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. 10668
    Prev
    Next
    INDEX
    Explanations

    salted hash

    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
    ும்
    1.46
    instruction
    1.21
     sự
    1.13
     ner
    1.09
    在
    1.05
    με
    1.04
     rum
    1.03
     instruction
    1.03
    귄
    1.03
     следует
    1.03
    POSITIVE LOGITS
    lə
    1.43
    lir
    1.25
    går
    1.25
    רג
    1.24
    kannya
    1.24
    lés
    1.21
    ర
    1.18
    ল
    1.17
     बताऊंगा
    1.14
    ského
    1.12
    Activations Density 0.006%

    No Known Activations