© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 13228
    Prev
    Next
    INDEX
    Explanations

    remember

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
    祎
    0.48
    ್ಯೂ
    0.45
     bootstrapping
    0.44
     bootstrap
    0.44
    ATUM
    0.43
    ಾರ
    0.42
     Status
    0.42
    ძლი
    0.42
    珽
    0.41
    韬
    0.41
    POSITIVE LOGITS
     remember
    4.91
    remember
    4.78
     remembers
    4.66
     remembered
    4.63
     기억
    4.63
     remembering
    4.53
     Remember
    4.47
    Remember
    4.44
     memory
    4.31
    記憶
    4.22
    Activations Density 0.323%

    No Known Activations