© 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-16K
    7. 714
    Prev
    Next
    INDEX
    Explanations

    without conditions or exceptions

    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
    меча
    3.17
    要
    3.11
     junit
    2.87
    ein
    2.81
     loosening
    2.73
    watercolor
    2.70
    ه
    2.69
     inguinal
    2.66
    毕竟
    2.65
     macam
    2.64
    POSITIVE LOGITS
     względu
    2.97
    te
    2.57
    Ꮖ
    2.54
     accès
    2.53
     Commencez
    2.52
    ম
    2.48
     metr
    2.47
    <0x80>
    2.46
    ని
    2.46
    д
    2.44
    Activations Density 0.439%

    No Known Activations