© 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. 98862
    Prev
    Next
    INDEX
    Explanations

    no such thing as

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

    assigning aliases with AS

    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
     Biochem
    0.42
     ชั่วโมง
    0.41
     മു
    0.41
     நாக
    0.41
     получать
    0.40
     дві
    0.39
    決して
    0.39
     」
    0.38
     पाएं
    0.37
    厳
    0.37
    POSITIVE LOGITS
     as
    0.92
     sebagai
    0.92
    作为
    0.89
    として
    0.84
     হিসেবে
    0.80
     ως
    0.80
     તરીકે
    0.79
    としての
    0.77
     作为
    0.76
     Sebagai
    0.70
    Activations Density 0.006%

    No Known Activations