© 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. 1125
    Prev
    Next
    INDEX
    Explanations

    ending punctuation

    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
    ς
    0.94
     claro
    0.89
     बार
    0.89
     an
    0.87
     વખતે
    0.84
    其他
    0.83
     এক
    0.82
    是
    0.82
     primeiro
    0.82
    Ο
    0.82
    POSITIVE LOGITS
    m
    1.00
    .}$
    0.99
    ર
    0.94
    𝘪
    0.91
    or
    0.91
    ie
    0.90
    as
    0.90
    fyp
    0.89
    м
    0.86
    ির
    0.84
    Activations Density 0.002%

    No Known Activations