© 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. 15103
    Prev
    Next
    INDEX
    Explanations

    last followed by ending noun

    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
    踞
    1.29
    putation
    1.21
    擒
    1.10
    oree
    1.10
     legen
    1.08
    爯
    1.07
     eftersom
    1.04
     kaikki
    1.04
    ⇣
    1.03
    iksaan
    1.02
    POSITIVE LOGITS
    ம்
    1.26
    ित
    1.16
    s
    1.07
    ists
    1.05
    ය
    1.05
    t
    1.02
    ط
    1.01
    tive
    1.00
     możli
    0.99
     struct
    0.99
    Activations Density 0.001%

    No Known Activations