© 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. 178539
    Prev
    Next
    INDEX
    Explanations

    powder dust or out of limits

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

    curious you seeking

    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
     நோய
    0.41
     счастли
    0.41
     longed
    0.40
     squirrels
    0.39
     еже
    0.39
     EL
    0.39
     आणखी
    0.38
     דער
    0.38
     ሌ
    0.38
     лам
    0.38
    POSITIVE LOGITS
     audition
    0.46
     gyr
    0.45
    气息
    0.44
     Maier
    0.42
    会被
    0.42
    ských
    0.42
    σκε
    0.41
     üzere
    0.41
     mesto
    0.40
     rencont
    0.40
    Activations Density 0.001%

    No Known Activations