© 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. 43570
    Prev
    Next
    INDEX
    Explanations

    humectant or -ant suffix

    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
    fillRect
    0.59
    わ
    0.59
     sweaty
    0.57
     Dmitri
    0.56
    liners
    0.55
    mapped
    0.55
     হাউ
    0.54
    gebaut
    0.54
     cramped
    0.53
    guessed
    0.53
    POSITIVE LOGITS
    il
    1.07
    b
    0.93
    م
    0.93
    ва
    0.91
    ir
    0.90
    n
    0.87
    au
    0.86
    o
    0.86
    aj
    0.84
    נ
    0.84
    Activations Density 0.000%

    No Known Activations