© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2359
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words

    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
    ️⃣
    0.38
    č
    0.36
    ن
    0.35
    nél
    0.34
    stärke
    0.33
    ↵↵
    0.32
    า
    0.32
    ча
    0.32
    n
    0.32
     genießen
    0.32
    POSITIVE LOGITS
     I
    0.49
     in
    0.46
     Ι
    0.38
     کی۔
    0.38
    IA
    0.38
    II
    0.36
    IO
    0.35
    Ο
    0.34
    А
    0.34
     Υ
    0.33
    Activations Density 0.001%

    No Known Activations