© 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. 66985
    Prev
    Next
    INDEX
    Explanations

    entities and following words

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

    social academics

    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
     শত
    0.53
    новништво
    0.51
     genug
    0.48
     แปร
    0.47
    ляє
    0.47
    𒁀
    0.47
     डिफ
    0.46
    xavier
    0.46
    ਾਲ
    0.45
    ществ
    0.45
    POSITIVE LOGITS
     ED
    0.57
     H
    0.54
     ENTER
    0.54
     express
    0.54
     K
    0.53
     conglomerates
    0.53
     integro
    0.53
     IT
    0.52
     EST
    0.52
     ERROR
    0.52
    Activations Density 0.000%

    No Known Activations