© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 223802
    Prev
    Next
    INDEX
    Explanations

    RFID technology

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

    less X more Y

    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
     progression
    0.55
    ंशिक
    0.48
     village
    0.46
    ও
    0.44
    бре
    0.43
     darker
    0.43
     patho
    0.43
     well
    0.42
     hamlet
    0.41
    ரி
    0.40
    POSITIVE LOGITS
     黃
    0.53
    ORE
    0.51
     多い
    0.49
    OPH
    0.48
     చర్చ
    0.48
     τρο
    0.48
     OPEC
    0.48
     เงี้ย
    0.47
    ners
    0.47
    UG
    0.46
    Activations Density 0.000%

    No Known Activations