© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3694
    Prev
    Next
    INDEX
    Explanations

    contact, connect, suggest, impress, invest

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     naquele
    0.60
    ளோ
    0.60
    㕲
    0.59
    Бахар
    0.54
     Afterward
    0.54
    ববার
    0.52
     naquela
    0.51
    㭋
    0.51
    nemonic
    0.51
     özelliği
    0.51
    POSITIVE LOGITS
    وا
    0.82
    s
    0.78
    ance
    0.76
    sche
    0.76
    ed
    0.75
    d
    0.75
     cryptography
    0.72
    Cryptography
    0.72
     encryption
    0.72
    sion
    0.72
    Activations Density 0.188%

    No Known Activations