© 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. 10329
    Prev
    Next
    INDEX
    Explanations

    serif fonts

    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
     annan
    2.31
    து
    2.31
    cstdlib
    2.29
    ل
    2.23
    oğlu
    2.20
    ities
    2.16
     समर्पित
    2.05
     siguiente
    2.00
    ל
    1.98
    tg
    1.96
    POSITIVE LOGITS
    hetical
    2.15
    ने
    2.02
     colonial
    2.01
     увиде
    1.87
    ोह
    1.79
    democratic
    1.78
     blank
    1.75
     bloody
    1.75
    𝒆
    1.70
    िक
    1.67
    Activations Density 0.002%

    No Known Activations