© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11914
    Prev
    Next
    INDEX
    Explanations

    Option

    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
    ل
    2.48
    ри
    2.40
    arov
    2.32
    ្នុង
    2.31
    ﺭ
    2.24
    𝚂
    2.23
    ovne
    2.22
    sheets
    2.21
    스럽
    2.15
    oons
    2.12
    POSITIVE LOGITS
    en
    3.02
    ный
    2.65
    ally
    2.58
    ly
    2.54
    mselves
    2.52
    ು
    2.51
    west
    2.45
    nya
    2.29
    ные
    2.29
    िक
    2.29
    Activations Density 0.032%

    No Known Activations