© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 209942
    Prev
    Next
    INDEX
    Explanations

    recalling past events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    looking
    0.42
     innocence
    0.42
     глаза
    0.40
    ܚ
    0.40
    ແບບ
    0.39
    𒌋
    0.39
    Amérique
    0.39
     býval
    0.39
    amaged
    0.39
    níci
    0.39
    POSITIVE LOGITS
     कोणते
    0.41
     끌
    0.41
     sair
    0.40
     alla
    0.39
     Dib
    0.38
     Genome
    0.38
     serialize
    0.37
    导
    0.37
     Gen
    0.37
     Microbiology
    0.37
    Activations Density 0.002%

    No Known Activations