© 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. 31-GEMMASCOPE-2-RES-262K
    7. 112862
    Prev
    Next
    INDEX
    Explanations

    power, machines, encouragement, accuracy, strength

    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_31_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
     පළ
    0.41
     Pharisees
    0.41
    {
    0.40
    تان
    0.40
    さて
    0.40
    ubre
    0.40
     だ
    0.40
    եղ
    0.39
     よ
    0.39
    {(-
    0.39
    POSITIVE LOGITS
     optimizations
    0.52
     optimizing
    0.48
     ένας
    0.47
     kvalitet
    0.46
     europe
    0.46
     defocus
    0.45
     thermodynamic
    0.45
     príncipe
    0.44
    ুয়াল
    0.44
     Príncipe
    0.43
    Activations Density 0.006%

    No Known Activations