© 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. 95599
    Prev
    Next
    INDEX
    Explanations

    reports and statistics

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

    time periods

    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
    必要があります
    0.45
     Über
    0.42
    englisch
    0.41
    खा
    0.40
     {#
    0.40
    Über
    0.40
     controlado
    0.40
    Eng
    0.39
     সুরক্ষিত
    0.39
    Describes
    0.39
    POSITIVE LOGITS
     strollers
    0.44
     hostel
    0.42
     apna
    0.42
    痘
    0.42
     léč
    0.41
    了嗎
    0.40
     bezoek
    0.40
     classmates
    0.40
     हैप्पी
    0.39
     préciser
    0.39
    Activations Density 0.000%

    No Known Activations