© 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. 8769
    Prev
    Next
    INDEX
    Explanations

    explanation, exploration, involving, example

    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
    ты
    1.48
    ፥
    1.46
    .}$
    1.38
     dwRes
    1.36
     лидер
    1.30
    of
    1.29
     glimpses
    1.29
    که
    1.28
    жа
    1.26
    รถ
    1.24
    POSITIVE LOGITS
    ammlung
    2.03
    e
    1.84
    o
    1.64
    dob
    1.59
    oretically
    1.56
    quela
    1.55
    dür
    1.50
    kette
    1.49
    n
    1.49
    ing
    1.48
    Activations Density 0.000%

    No Known Activations