© 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. 10846
    Prev
    Next
    INDEX
    Explanations

    what questions and clauses

    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
    er
    2.69
    ر
    2.40
    ic
    2.40
    ה
    2.36
    ার
    2.19
    り
    2.05
    a
    2.04
    р
    2.04
    ょう
    1.97
    𝘳
    1.96
    POSITIVE LOGITS
     betre
    2.15
    റ്റ്
    2.11
    tting
    2.05
    soever
    1.97
     eren
    1.94
    е
    1.91
    റ്റം
    1.89
    mActivity
    1.85
    চ
    1.83
    ্ট
    1.82
    Activations Density 0.182%

    No Known Activations