© 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. 7595
    Prev
    Next
    INDEX
    Explanations

    bulk candy types

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

    at least

    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
    قی
    0.39
     presiden
    0.37
    রেক
    0.36
    綗
    0.36
     semangat
    0.36
     pinnacle
    0.35
     celebratory
    0.35
     dokt
    0.35
     পরিকল্প
    0.35
     MyApp
    0.35
    POSITIVE LOGITS
    Factor
    0.39
    Slot
    0.38
    Ӏ
    0.38
    аб
    0.37
    ayo
    0.37
    Р
    0.37
    Tab
    0.35
    Ain
    0.35
    с
    0.34
    ass
    0.34
    Activations Density 0.043%

    No Known Activations