© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 205453
    Prev
    Next
    INDEX
    Explanations

    color, box, code

    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_40_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
    ;">
    0.37
    mars
    0.37
     false
    0.36
    False
    0.36
    !=
    0.36
     Scaling
    0.36
    ình
    0.35
    outine
    0.35
     Pix
    0.35
     False
    0.35
    POSITIVE LOGITS
     philanthrop
    0.45
     darkened
    0.42
     darkening
    0.42
     planners
    0.41
     \%,
    0.41
     diaper
    0.41
    प्ट
    0.40
     barter
    0.39
    \%),
    0.39
    নু
    0.39
    Activations Density 0.003%

    No Known Activations