© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13360
    Prev
    Next
    INDEX
    Explanations

    performance evaluation

    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
    te
    3.12
    ر
    3.07
    ल
    3.01
    ส์
    2.73
    ка
    2.72
    ु
    2.69
    us
    2.68
    на
    2.57
    k
    2.52
     overpowering
    2.47
    POSITIVE LOGITS
    𝐢
    4.36
    𝐨
    3.91
    𝐫
    3.90
    𝐚
    3.71
    𝐮
    3.64
    𝐧
    3.56
    𝐞
    3.55
    𝐝
    3.42
    𝐬
    3.30
    𝐥
    3.21
    Activations Density 0.254%

    No Known Activations