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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3490
    Prev
    Next
    INDEX
    Explanations

    multi-script words

    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_16k_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
    y
    1.16
    PIL
    1.09
    י
    1.09
    Ин
    1.02
     नयी
    0.98
    ಿಗ
    0.97
     první
    0.97
    eastern
    0.97
    ఉ
    0.97
     a
    0.93
    POSITIVE LOGITS
    কে
    1.49
     haue
    1.39
    ться
    1.36
    ți
    1.31
    ,(
    1.29
    تے
    1.28
    นี้
    1.28
     utilises
    1.27
     undergoes
    1.25
    áme
    1.25
    Activations Density 0.303%

    No Known Activations