© 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. 183751
    Prev
    Next
    INDEX
    Explanations

    UAH visas

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

    diverse variations

    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
    y
    0.52
    协议
    0.50
    头
    0.50
     Communications
    0.47
    раху
    0.47
    ду
    0.46
    Ко
    0.46
    頭
    0.45
    i
    0.45
    1
    0.44
    POSITIVE LOGITS
     noteworthy
    0.54
    والفقار
    0.49
     سکے۔
    0.49
     ذریع
    0.48
    sendPluginResult
    0.48
    bridges
    0.47
    OLYBD
    0.46
     एप्ली
    0.46
    graphHead
    0.46
     muối
    0.46
    Activations Density 0.000%

    No Known Activations