© 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. 48568
    Prev
    Next
    INDEX
    Explanations

    support they receive

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

    avoid mentioning

    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
     capitalise
    0.49
     deactivate
    0.48
     wikipedia
    0.46
     zitten
    0.46
     usare
    0.46
     জানালেন
    0.46
     rectify
    0.46
     '');
    0.45
     softwares
    0.44
     mindset
    0.44
    POSITIVE LOGITS
    强
    0.49
    There
    0.47
    饮
    0.44
    Toward
    0.44
    时间
    0.43
    Fla
    0.42
    鸣
    0.42
    Members
    0.42
    强大
    0.42
    Migrations
    0.42
    Activations Density 0.000%

    No Known Activations