© 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-262K
    7. 88829
    Prev
    Next
    INDEX
    Explanations

    contrails and list files

    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
    ка
    0.67
    ב
    0.61
    か
    0.61
    да
    0.60
    ค่ะ
    0.60
     calitate
    0.58
     ignorant
    0.55
    つ
    0.55
    ユー
    0.55
    י
    0.54
    POSITIVE LOGITS
     प्रोत्सा
    0.62
    a
    0.61
    newsletter
    0.59
    Updating
    0.56
     Updating
    0.56
    ritten
    0.56
    writer
    0.55
    rég
    0.55
    updating
    0.54
    log
    0.53
    Activations Density 0.000%

    No Known Activations