© 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. 13134
    Prev
    Next
    INDEX
    Explanations

    remember and memorize

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

    memory and memorization

    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
    rospective
    0.47
    ብር
    0.46
     বিশ্লেষণ
    0.45
    璞
    0.45
     अनुभव
    0.45
    readValue
    0.44
    გუ
    0.43
    觫
    0.42
    кл
    0.41
    πισ
    0.41
    POSITIVE LOGITS
     Memor
    0.76
     memor
    0.75
     memorize
    0.72
    Memor
    0.70
    记住
    0.55
     Remembering
    0.55
     Retention
    0.54
     Memorandum
    0.53
    memor
    0.53
     retention
    0.51
    Activations Density 0.028%

    No Known Activations