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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35119
    Prev
    Next
    INDEX
    Explanations

    properties, crime, price volatility

    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
    न
    1.18
     egyszer
    1.05
     adsorb
    1.03
    Вы
    0.98
     endanger
    0.97
    '
    0.97
    م
    0.96
    Боль
    0.96
     aque
    0.95
     ascend
    0.95
    POSITIVE LOGITS
    ді
    1.08
     生命周期函数
    1.05
    et
    1.04
     ແລະ
    1.03
    ورٹی
    1.02
    ructuring
    0.98
    няя
    0.98
    蚣
    0.97
    rà
    0.96
    ються
    0.94
    Activations Density 0.000%

    No Known Activations