© 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-262K
    7. 44854
    Prev
    Next
    INDEX
    Explanations

    crucial details or steps

    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
    to
    2.28
    the
    2.19
    t
    1.94
    r
    1.91
    as
    1.79
    у
    1.77
    𝗴
    1.74
    l
    1.69
    지난
    1.68
    tox
    1.66
    POSITIVE LOGITS
    ا
    3.11
    ం
    2.11
    ை
    1.86
    י
    1.84
     وعلى
    1.82
     Нужно
    1.70
    ן
    1.66
    い
    1.64
    ым
    1.63
    ي
    1.62
    Activations Density 0.053%

    No Known Activations