© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71268
    Prev
    Next
    INDEX
    Explanations

    becoming increasingly

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

    numbers and words following them

    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
    Negative Logits
     adapté
    0.52
     appet
    0.46
     stalking
    0.46
     လ
    0.44
     stalling
    0.44
    adder
    0.43
     CAL
    0.43
     administrativos
    0.43
    ทาน
    0.42
     nuis
    0.42
    POSITIVE LOGITS
     heißt
    0.50
    nullptr
    0.47
    ika
    0.46
     fifo
    0.46
    um
    0.45
    nYou
    0.45
    ঃ
    0.44
    ir
    0.43
     keluarga
    0.43
    이번
    0.43
    Activations Density 0.001%

    No Known Activations