© 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. 83740
    Prev
    Next
    INDEX
    Explanations

    alternative, lacking, degree

    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
    ys
    0.52
     base
    0.45
     thickness
    0.45
     substit
    0.44
     न्यूयॉर्क
    0.43
     asterisk
    0.43
     Base
    0.43
     ^
    0.42
     substitute
    0.41
    0.41
    POSITIVE LOGITS
     イメージ
    0.53
     Gewalt
    0.52
     ফাইল
    0.48
    IZING
    0.48
     åter
    0.47
    entliche
    0.47
     caves
    0.47
     епи
    0.46
     retreats
    0.46
    怒
    0.45
    Activations Density 0.003%

    No Known Activations