© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10508
    Prev
    Next
    INDEX
    Explanations

    suggests information or findings

    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
    i
    1.83
    י
    1.37
    ت
    1.32
    ر
    1.32
    ی
    1.32
    이
    1.27
    त
    1.25
    ي
    1.25
    й
    1.20
    ل
    1.20
    POSITIVE LOGITS
     investigación
    1.12
     sanguí
    1.11
    ievable
    1.11
     раствор
    1.10
     Однако
    1.09
    Сегодня
    1.08
    淈
    1.07
     undis
    1.06
    desIP
    1.03
     clogged
    1.03
    Activations Density 0.052%

    No Known Activations