© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 1197
    Prev
    Next
    INDEX
    Explanations

    numbers and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_65k_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
     válto
    0.52
     peinture
    0.52
    Portrait
    0.50
    اري
    0.50
     زي
    0.49
     ゼ
    0.48
     stvari
    0.48
     ត
    0.48
     asistente
    0.48
     Kud
    0.47
    POSITIVE LOGITS
    kec
    0.51
    ά
    0.46
     exif
    0.42
    fou
    0.42
    elabel
    0.42
     रवाना
    0.41
    ็ด
    0.41
     adjourned
    0.41
     ανε
    0.41
    ールの
    0.41
    Activations Density 0.000%

    No Known Activations