© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5111
    Prev
    Next
    INDEX
    Explanations

    suffix -er, -izer, -ger, decoder

    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
    те
    1.13
    ا
    1.07
     तरह
    1.05
    ﻞ
    1.05
    ्स
    1.02
    ность
    1.00
    י
    1.00
    스러
    0.99
    ﺮ
    0.99
    ط
    0.98
    POSITIVE LOGITS
    <bos>
    0.98
     extraordinaire
    0.96
    ‍♀️
    0.96
    ,
    0.95
     Ss
    0.93
    er
    0.92
    ר
    0.88
     Distributor
    0.87
     Exp
    0.87
    et
    0.86
    Activations Density 0.170%

    No Known Activations