© 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. 156969
    Prev
    Next
    INDEX
    Explanations

    honour students

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

    descriptions that indicate change or difference

    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
     neh
    0.45
    Three
    0.43
    +'/
    0.42
    HttpPost
    0.42
    Hop
    0.41
    WB
    0.40
    Charges
    0.40
    Hub
    0.39
    wb
    0.39
     bathtub
    0.39
    POSITIVE LOGITS
    羵
    0.54
     отде
    0.50
    ignore
    0.49
     술
    0.48
     আরেকটি
    0.46
     имму
    0.46
    నాల
    0.46
     specialize
    0.46
     قي
    0.46
     мотива
    0.46
    Activations Density 0.000%

    No Known Activations