© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 675
    Prev
    Next
    INDEX
    Explanations

    through automation, because the

    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
    י
    2.33
    ی
    2.20
    ি
    2.06
    i
    1.65
    ي
    1.52
    не
    1.44
    ி
    1.40
    м
    1.32
    й
    1.29
    ان
    1.24
    POSITIVE LOGITS
    𝐬
    1.33
    𝐫
    1.29
    𝘮
    1.25
    𝘴
    1.23
     dint
    1.19
     prostu
    1.16
    𝘞
    1.16
    𝐛
    1.15
     adanya
    1.15
    픈
    1.14
    Activations Density 0.757%

    No Known Activations