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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8851
    Prev
    Next
    INDEX
    Explanations

    mitigation strategies

    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
    आई
    2.14
    ON
    2.09
    était
    2.03
    theless
    1.90
    Ə
    1.83
    AY
    1.81
    Ý
    1.77
    面的
    1.77
    İ
    1.76
    Ğ
    1.75
    POSITIVE LOGITS
    c
    2.11
    gawa
    1.99
    ut
    1.91
    quela
    1.88
    y
    1.87
    ર
    1.84
    hen
    1.79
     Malware
    1.79
     дела
    1.76
    ján
    1.73
    Activations Density 0.009%

    No Known Activations