© 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. 45374
    Prev
    Next
    INDEX
    Explanations

    associated bits ? Get Explore know gap Enter Preserve Season

    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
    ly
    0.86
    their
    0.81
    𝕒
    0.81
    lo
    0.78
    ು
    0.77
    щення
    0.75
    昷
    0.75
    ામ
    0.74
    to
    0.74
    otham
    0.73
    POSITIVE LOGITS
     возможность
    1.12
     atualização
    0.92
     هیچ
    0.84
    сны
    0.84
     съем
    0.84
    ็ด
    0.82
     размеры
    0.80
     absolutamente
    0.80
     possibilidade
    0.80
     доступны
    0.80
    Activations Density 0.000%

    No Known Activations