© 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-16K
    7. 11320
    Prev
    Next
    INDEX
    Explanations

    dates and price ranges

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

    numbers like 3 and 7

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    пози
    0.46
    ambarkan
    0.45
    posición
    0.44
    鶉
    0.44
    жко
    0.43
    жку
    0.42
    avar
    0.42
    новен
    0.40
    ಾಗಿ
    0.40
    д
    0.40
    POSITIVE LOGITS
     Pilot
    0.53
    Pilot
    0.48
     pilot
    0.46
     Pilots
    0.46
     soient
    0.42
     haute
    0.39
     Tough
    0.38
     ï
    0.38
    ̥
    0.38
     Cow
    0.38
    Activations Density 0.001%

    No Known Activations