© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 9824
    Prev
    Next
    INDEX
    Explanations

    years of

    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
    ،
    1.22
     захворю
    1.20
    ๕
    1.19
    ท์
    1.18
     itibaren
    1.16
    媝
    1.16
    brev
    1.14
    ፣
    1.13
    เรา
    1.12
    ])):
    1.12
    POSITIVE LOGITS
    !\!\
    1.24
    n
    1.24
    ным
    1.20
    ن
    1.16
    ب
    1.14
    ্ন
    1.13
    েও
    1.13
     μαζί
    1.12
    <0xC2>
    1.10
     বড়
    1.10
    Activations Density 0.013%

    No Known Activations