© 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. 190230
    Prev
    Next
    INDEX
    Explanations

    processing, shipping, and giving gifts

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

    information warfare and automated construction

    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
    dL
    0.46
    ﻤ
    0.45
    øst
    0.44
     matchups
    0.43
    POOL
    0.43
    Pooling
    0.42
    婶
    0.42
    dim
    0.41
     skaters
    0.41
     camaraderie
    0.41
    POSITIVE LOGITS
    нига
    0.46
     হত্যাকাণ্ড
    0.44
     Acres
    0.42
     নিতান্ত
    0.42
     καθώς
    0.41
    任意
    0.41
     বুদ্ধ
    0.40
    禿
    0.40
     iccad
    0.40
     Само
    0.40
    Activations Density 0.001%

    No Known Activations