© 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-16K
    7. 1163
    Prev
    Next
    INDEX
    Explanations

    term's, criteria:

    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_16k_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
    ার
    1.19
     जिस
    1.16
    ্দ
    1.11
    anded
    1.10
    ed
    1.10
    nade
    1.08
    ượt
    1.07
    y
    1.06
    िक
    1.05
    utilized
    1.02
    POSITIVE LOGITS
     oldukça
    1.30
    %
    1.24
     virtues
    1.20
     remarkably
    1.17
    .%
    1.11
     einen
    1.10
     wichtigsten
    1.10
     SEXUAL
    1.10
     eine
    1.09
     ένα
    1.08
    Activations Density 1.786%

    No Known Activations