© 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. 193927
    Prev
    Next
    INDEX
    Explanations

    record preservation

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

    describing feelings or states

    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
     promotions
    0.42
    ahari
    0.42
    ))))
    0.42
     छठी
    0.42
    )))
    0.41
    ikh
    0.41
    ↵
    0.41
    이지만
    0.41
     devoted
    0.41
     Theft
    0.41
    POSITIVE LOGITS
    ли
    0.57
     vro
    0.53
    珉
    0.52
    সাই
    0.50
    роў
    0.49
    ตู
    0.48
    linetype
    0.48
    ╿
    0.48
    ход
    0.47
    ادة
    0.47
    Activations Density 0.001%

    No Known Activations