© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95824
    Prev
    Next
    INDEX
    Explanations

    browse other questions

    np_acts-logits-general · gemini-2.5-flash-lite

    triple talaq, config with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    את
    0.45
    使用
    0.44
    }/
    0.43
    region
    0.43
    ?/
    0.43
     Į
    0.43
     nějak
    0.42
     गाया
    0.42
    首先
    0.42
    部分的
    0.41
    POSITIVE LOGITS
    یده
    0.56
     conceptos
    0.49
     conceito
    0.47
     slogans
    0.47
    ный
    0.46
     seterusnya
    0.46
     собы
    0.46
    的状态
    0.45
    쾺
    0.45
    🚭
    0.44
    Activations Density 0.000%

    No Known Activations