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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1564
    Prev
    Next
    INDEX
    Explanations

    low, glum, free, dealt, throne, sight

    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_9_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
    𝐡
    1.50
    𝐬
    1.45
    𝐯
    1.43
    𝐛
    1.42
    𝐩
    1.37
    𝐨
    1.35
    𝐭
    1.35
    𝐝
    1.29
    𝐚
    1.27
    𝐫
    1.23
    POSITIVE LOGITS
    s
    1.30
    ల
    1.20
    sure
    1.20
     sorrows
    1.16
    ு
    1.16
    ve
    1.13
    g
    1.13
    ের
    1.09
    soul
    1.07
    t
    1.06
    Activations Density 0.207%

    No Known Activations