© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 10744
    Prev
    Next
    INDEX
    Explanations

    significant quantity, level, or degree

    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
    al
    3.13
    jší
    2.93
    های
    2.91
    𝐣
    2.89
    ോ
    2.83
    у
    2.79
    कर
    2.79
     acronym
    2.70
     significance
    2.66
    ত
    2.66
    POSITIVE LOGITS
    ٠
    2.58
     stenosis
    2.51
    ی
    2.41
    ١
    2.38
    ⟺
    2.31
    Markdown
    2.23
    Invitrogen
    2.15
    heel
    2.15
    ٣
    2.14
     protr
    2.13
    Activations Density 0.076%

    No Known Activations