© 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. 1824
    Prev
    Next
    INDEX
    Explanations

    here for

    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
    اً
    0.69
    ڈا
    0.63
    Idioma
    0.59
     لاءِ
    0.59
    ARAJYA
    0.59
     মেয়ে
    0.58
    ssä
    0.57
    К
    0.57
    ﺔ
    0.57
    ETERS
    0.57
    POSITIVE LOGITS
    .
    1.01
    ’
    0.88
    il
    0.80
    '
    0.79
     and
    0.67
    -
    0.67
    og
    0.63
    ila
    0.63
     packages
    0.63
     challenges
    0.62
    Activations Density 0.416%

    No Known Activations