© 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. 125617
    Prev
    Next
    INDEX
    Explanations

    open up

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

    carries the weight of history

    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
    仁
    0.52
    該
    0.49
    氯
    0.47
    正是
    0.47
    鄧
    0.46
    評論
    0.46
    вля
    0.45
    普
    0.45
    歌
    0.44
    коло
    0.43
    POSITIVE LOGITS
    hibition
    0.47
    spirational
    0.47
    plication
    0.46
     to
    0.45
     partnership
    0.45
    ocf
    0.44
     conoscere
    0.42
    olla
    0.42
    icorn
    0.42
    load
    0.42
    Activations Density 0.000%

    No Known Activations