© 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. 9790
    Prev
    Next
    INDEX
    Explanations

    separators and subsequent words like This

    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
    ্
    1.40
    Ɖ
    1.17
     radionuclide
    1.14
    .)
    1.13
    .).
    1.11
    ye
    1.09
    assertInstanceOf
    1.07
    bed
    1.07
    cı
    1.07
    jLabel
    1.06
    POSITIVE LOGITS
    ت
    1.12
    трима
    1.08
    ोस
    1.07
     машину
    1.05
    ાઓ
    1.03
    𝐨
    1.01
    单个
    1.01
    只
    1.01
    定番
    0.99
    有
    0.99
    Activations Density 0.002%

    No Known Activations