© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6095
    Prev
    Next
    INDEX
    Explanations

    avoiding the letter "e"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    뷁
    1.46
    ﻅ
    1.45
     Bakın
    1.44
     gyors
    1.44
     zabaw
    1.44
     medo
    1.42
     سطح
    1.38
     खूब
    1.38
     պատ
    1.37
     množství
    1.37
    POSITIVE LOGITS
    er
    0.90
    ↵↵
    0.90
    a
    0.85
    her
    0.84
     airline
    0.81
     adjuster
    0.81
     enrolment
    0.80
    <eos>
    0.80
     registrant
    0.78
    cert
    0.77
    Activations Density 0.000%

    No Known Activations