© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 45198
    Prev
    Next
    INDEX
    Explanations

    market-based solutions, rates, processes

    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
    ﯼ
    1.34
    ﺯ
    1.34
    ﺏ
    1.32
     שלו
    1.27
    ﺹ
    1.27
     Oxide
    1.26
     batas
    1.26
     poderos
    1.22
    يل
    1.20
     Chapters
    1.20
    POSITIVE LOGITS
    ა
    1.80
    氇
    1.76
    hesda
    1.67
    ка
    1.61
    ylsulfanyl
    1.59
    dude
    1.59
    er
    1.54
    είου
    1.53
    ानंतर
    1.53
    ensión
    1.51
    Activations Density 0.001%

    No Known Activations