© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11088
    Prev
    Next
    INDEX
    Explanations

    peace of mind

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

    reassurance and safety

    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_40_width_16k_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
     흥
    0.41
     revolution
    0.41
     হারা
    0.39
    逑
    0.39
     helst
    0.38
    ̽
    0.37
    儸
    0.37
    を超える
    0.37
    呛
    0.37
    Starburst
    0.36
    POSITIVE LOGITS
    安心
    2.11
    放心
    2.03
    安心して
    2.00
     reassured
    1.58
     worry
    1.53
     reassurance
    1.53
     安心
    1.48
     reassuring
    1.47
     reassure
    1.46
     Worry
    1.43
    Activations Density 0.482%

    No Known Activations