© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35363
    Prev
    Next
    INDEX
    Explanations

    whitespace removal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    dır
    2.30
    ר
    2.20
    ра
    1.78
    deki
    1.73
    ು
    1.70
    ﻝ
    1.70
    tia
    1.68
    trex
    1.63
     volna
    1.62
    tarif
    1.61
    POSITIVE LOGITS
    ні
    1.62
     불구하고
    1.52
    .}$
    1.50
    ীর
    1.44
    ı
    1.42
    نا
    1.41
    тия
    1.35
    ֿ
    1.35
    𝘯
    1.34
     Projek
    1.33
    Activations Density 0.001%

    No Known Activations