© 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. 2404
    Prev
    Next
    INDEX
    Explanations

    mind and punctuation

    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
    íonn
    1.26
     quím
    1.22
    ारण
    1.22
    नाडु
    1.21
    闓
    1.19
    ულია
    1.17
    usepackage
    1.15
    ']==
    1.13
     jaaye
    1.13
    ಿಂತ
    1.13
    POSITIVE LOGITS
    .
    2.53
    。
    1.92
    ."
    1.85
    .“
    1.65
    .”
    1.62
    ).
    1.61
    !
    1.55
    ।
    1.54
    ..
    1.52
    .`
    1.51
    Activations Density 2.412%

    No Known Activations