Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8475
    Prev
    Next
    INDEX
    Explanations

    you are / I have

    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
    j
    0.93
    is
    0.86
    ль
    0.80
    ig
    0.75
    ш
    0.72
     elucid
    0.71
    ir
    0.71
    жа
    0.70
     apportionment
    0.69
    ot
    0.68
    POSITIVE LOGITS
    EO
    0.77
     Rakyat
    0.69
    '
    0.69
     Ancak
    0.63
     但是
    0.62
    >
    0.62
    Rich
    0.61
     Tahun
    0.61
     Και
    0.60
    EM
    0.59
    Activations Density 0.857%

    No Known Activations