© 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. 28355
    Prev
    Next
    INDEX
    Explanations

    when it is appropriate

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

    neural voices, divine feminine

    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
    または
    0.48
     または
    0.47
     будущего
    0.47
    ondon
    0.46
     じゃん
    0.45
    മായിരുന്നു
    0.44
    箇
    0.44
     だっ
    0.44
     通知
    0.43
    apas
    0.42
    POSITIVE LOGITS
     akust
    0.48
     yaptı
    0.46
     próp
    0.46
    ڵی
    0.44
     çocuklar
    0.44
     gyerek
    0.44
     différence
    0.43
     figlia
    0.42
     Kā
    0.42
     الفي
    0.42
    Activations Density 0.002%

    No Known Activations