© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3026
    Prev
    Next
    INDEX
    Explanations

    index `i` or `i-1`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    s
    1.45
    deposit
    1.34
    saf
    1.22
    cps
    1.16
    Deposit
    1.15
    en
    1.13
    Depos
    1.11
    kil
    1.11
    .*
    1.11
    nore
    1.08
    POSITIVE LOGITS
     décider
    1.74
     번째
    1.73
     decidir
    1.72
     decidió
    1.69
     që
    1.61
    旬
    1.60
    мену
    1.57
     nombr
    1.57
     pediu
    1.56
     optar
    1.56
    Activations Density 0.001%

    No Known Activations