© 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. 162827
    Prev
    Next
    INDEX
    Explanations

    pottery village and author

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

    forget simply personal

    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
     οποία
    0.57
     выигра
    0.49
    ២
    0.48
     гуляць
    0.47
     MOSFET
    0.46
    耔
    0.46
     photosynthesis
    0.46
     curcumin
    0.46
     баскет
    0.46
     大家
    0.46
    POSITIVE LOGITS
    å
    0.51
    á
    0.50
    illet
    0.49
    application
    0.48
    affirm
    0.48
    icom
    0.48
    ich
    0.47
    conditions
    0.47
    quot
    0.46
    old
    0.46
    Activations Density 0.000%

    No Known Activations