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. 8447
    Prev
    Next
    INDEX
    Explanations

    tell a story

    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
    к
    1.57
     troublesome
    1.54
    т
    1.52
     Archaeological
    1.45
    ს
    1.45
    이랑
    1.44
    ς
    1.40
    嘞
    1.40
     foreseeable
    1.38
    केजी
    1.36
    POSITIVE LOGITS
    lier
    1.98
    rä
    1.82
    ികിത്സ
    1.75
    ली
    1.66
    änen
    1.65
    ுள்ள
    1.64
    wür
    1.64
    ik
    1.63
    lik
    1.63
    ak
    1.59
    Activations Density 0.085%

    No Known Activations