© 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. 2956
    Prev
    Next
    INDEX
    Explanations

    states of being

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

    be + adjective or being + adjective

    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
     caches
    0.40
     可
    0.38
     isValid
    0.38
     不是
    0.38
     如果
    0.38
     అనేది
    0.38
    属于
    0.37
     就是
    0.37
     最
    0.36
     ನಮ್ಮ
    0.36
    POSITIVE LOGITS
     tempted
    0.58
     able
    0.57
     aware
    0.53
     unable
    0.53
     fortunate
    0.49
    unable
    0.49
     encouraged
    0.47
     intrigued
    0.47
     persuaded
    0.47
     surprised
    0.47
    Activations Density 0.467%

    No Known Activations