© 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. 8250
    Prev
    Next
    INDEX
    Explanations

    clarifying meaning or intent

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

    defining and referring

    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
     presenceData
    0.39
    oblast
    0.38
     comienzan
    0.37
     sogar
    0.37
    ⁶
    0.36
     thậm
    0.36
    ₁+
    0.36
     श्रे
    0.35
     ሞ
    0.35
    elfalt
    0.35
    POSITIVE LOGITS
    指的是
    0.89
     refers
    0.87
     referring
    0.84
     meant
    0.82
    という意味
    0.81
     maksud
    0.80
    的意思
    0.78
     refer
    0.76
     bedo
    0.74
     dimaksud
    0.73
    Activations Density 0.109%

    No Known Activations