© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9700
    Prev
    Next
    INDEX
    Explanations

    random, rand, Randy, Randall, Randolph

    np_acts-logits-general · gemini-2.5-flash-lite

    random number generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     عالمی
    0.40
    म्‍
    0.39
     dangere
    0.39
     incrível
    0.38
    थिंग
    0.38
    ﻗ
    0.38
    ificador
    0.37
     Giang
    0.36
    ⌋
    0.36
    remainder
    0.35
    POSITIVE LOGITS
     random
    0.49
     Random
    0.48
    ised
    0.47
    izer
    0.47
    izing
    0.45
    isierte
    0.45
    ized
    0.43
     rand
    0.42
     thoughts
    0.42
    thoughts
    0.41
    Activations Density 0.079%

    No Known Activations