© 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. 16242
    Prev
    Next
    INDEX
    Explanations

    seriously, custom, record, proven

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

    reveal different, laws from, Marketing focus

    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
    Et
    0.42
     Ио
    0.41
    浩
    0.41
     機
    0.40
    ইর
    0.40
    ко
    0.39
    ekte
    0.39
    โ
    0.39
    וד
    0.39
    ugly
    0.39
    POSITIVE LOGITS
    த்தால்
    0.55
     হইতেছে
    0.51
     আবাসিক
    0.49
     najbolje
    0.49
     করিতেছেন
    0.47
     आवासीय
    0.47
     পাচ্ছেন
    0.47
     undeveloped
    0.47
    वाया
    0.46
     putem
    0.46
    Activations Density 0.000%

    No Known Activations