© 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. 5663
    Prev
    Next
    INDEX
    Explanations

    location of phrases

    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
    ﺼ
    0.94
     истины
    0.91
     размеров
    0.90
     отсутствие
    0.89
     изделий
    0.89
     jueces
    0.88
    ﻖ
    0.88
     teorías
    0.87
     anuncios
    0.85
     сча
    0.85
    POSITIVE LOGITS
    in
    0.97
    ne
    0.95
    ar
    0.86
    t
    0.84
    s
    0.83
    at
    0.81
    d
    0.79
    an
    0.78
    al
    0.78
    ur
    0.77
    Activations Density 0.000%

    No Known Activations