© 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. 174936
    Prev
    Next
    INDEX
    Explanations

    salary packaging

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

    social media platforms

    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
     ankaŭ
    0.57
     također
    0.49
    hubungan
    0.48
    ᔨ
    0.47
    রামর্শ
    0.47
    lığını
    0.46
    უს
    0.46
    емая
    0.45
    ógrafo
    0.45
    ຟ
    0.44
    POSITIVE LOGITS
     десяти
    0.52
     大人
    0.52
    $>
    0.46
     unpredictable
    0.46
    SizeBytes
    0.45
    suc
    0.45
    かっ
    0.44
    (${
    0.44
     unpredict
    0.43
     worsen
    0.43
    Activations Density 0.001%

    No Known Activations