© 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. 31-GEMMASCOPE-2-RES-262K
    7. 142990
    Prev
    Next
    INDEX
    Explanations

    weeks of, or should

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

    what makes it then

    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_31_width_262k_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
    જ
    0.46
    Published
    0.46
    Latest
    0.45
     appealed
    0.43
     країни
    0.43
    olarmente
    0.42
     reliably
    0.42
    Statistics
    0.42
    ﻠ
    0.41
    Guest
    0.41
    POSITIVE LOGITS
     kapt
    0.47
    voren
    0.46
     그래프
    0.44
     saate
    0.44
     chunky
    0.44
     hasilnya
    0.42
     gyn
    0.42
     بده
    0.42
    руу
    0.41
     hamb
    0.40
    Activations Density 0.000%

    No Known Activations