© 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-262K
    7. 29145
    Prev
    Next
    INDEX
    Explanations

    entity names and following descriptors

    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_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
     ร
    0.64
     б
    0.63
     Б
    0.63
     спеціа
    0.62
     ر
    0.61
     คุณ
    0.60
    勰
    0.58
    電腦
    0.58
    InterfaceLine
    0.57
    Б
    0.57
    POSITIVE LOGITS
    id
    0.63
    ak
    0.60
     prostor
    0.56
     stanje
    0.55
     Namibia
    0.54
    ik
    0.54
    inh
    0.54
     ঘোষণার
    0.53
    fiscal
    0.53
     Estado
    0.52
    Activations Density 0.048%

    No Known Activations