© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 21141
    Prev
    Next
    INDEX
    Explanations

    ships and hangovers

    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
    \
    0.46
    izes
    0.43
    '
    0.42
    其他
    0.37
    ian
    0.34
    力量
    0.33
    ines
    0.33
     основной
    0.33
     manchas
    0.33
     autres
    0.32
    POSITIVE LOGITS
     a
    0.42
    Item
    0.41
    ر
    0.41
    ר
    0.40
    רת
    0.38
    רות
    0.37
    Resolution
    0.37
    Inscription
    0.36
     transporting
    0.35
    рного
    0.35
    Activations Density 0.001%

    No Known Activations