© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10247
    Prev
    Next
    INDEX
    Explanations

    where to

    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_22_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
    𝐢
    1.33
    tos
    1.29
    রি
    1.23
    tion
    1.15
    tie
    1.13
    یہ
    1.13
    ipped
    1.12
    tic
    1.11
    یز
    1.10
    ită
    1.10
    POSITIVE LOGITS
    fore
    1.56
    abouts
    1.51
    ን
    1.33
     родился
    1.33
    acuse
    1.30
    ן
    1.27
     учета
    1.19
    heids
    1.17
     불구하고
    1.13
    abody
    1.12
    Activations Density 0.039%

    No Known Activations