© 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. 148645
    Prev
    Next
    INDEX
    Explanations

    location and descriptive terms

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

    identifying places and wins

    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
    setdefault
    0.49
    setLocation
    0.48
     겨
    0.47
     commencent
    0.46
    urin
    0.45
     lattice
    0.45
     terão
    0.43
    )~
    0.43
     Diver
    0.43
    ⎟
    0.43
    POSITIVE LOGITS
    כה
    0.48
    មូល
    0.48
    ﻙ
    0.47
     adjectives
    0.46
     stammt
    0.46
     Gründe
    0.46
     codewords
    0.46
    人气
    0.45
    াজি
    0.45
    িলিয়া
    0.45
    Activations Density 0.001%

    No Known Activations