© 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. 10569
    Prev
    Next
    INDEX
    Explanations

    published by, property rights, belief

    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
    দ্ভুত
    1.51
    owań
    1.30
    ﻩ
    1.20
    toFixed
    1.15
     batas
    1.14
    ezas
    1.13
     destacan
    1.10
     tanh
    1.09
     lhs
    1.07
     dtype
    1.05
    POSITIVE LOGITS
    вЂ
    1.23
    vm
    1.22
    डॉ
    1.18
    Voor
    1.13
    आ
    1.10
     -------
    1.09
    Роз
    1.09
     fact
    1.09
    -\
    1.08
    ጀመሪያ
    1.07
    Activations Density 0.000%

    No Known Activations