© 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-262K
    7. 9733
    Prev
    Next
    INDEX
    Explanations

    operating ability

    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_262k_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
    S
    1.51
     (
    1.33
    6
    1.19
    m
    1.18
     seseorang
    1.16
     Begriff
    1.13
    /
    1.12
    (
    1.11
    7
    1.11
     tahun
    1.08
    POSITIVE LOGITS
    获取
    2.19
    必须
    2.14
     moisturizing
    2.14
    瑢
    2.12
     可以
    2.09
     desirable
    2.07
    采用
    2.07
     advisable
    2.05
    解决
    2.04
    降低
    2.01
    Activations Density 0.010%

    No Known Activations