© 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. 94227
    Prev
    Next
    INDEX
    Explanations

    words following specific terms

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

    travel itineraries and plans

    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
    cloudinary
    0.61
    dropbox
    0.59
    zí
    0.57
    jen
    0.57
    jab
    0.55
    paid
    0.54
    }({\
    0.54
    zi
    0.53
    textarea
    0.52
    rei
    0.52
    POSITIVE LOGITS
     n
    0.49
    n
    0.47
     guts
    0.42
    Mont
    0.41
     lite
    0.41
     lutter
    0.41
     magn
    0.40
     l
    0.40
    AKER
    0.40
     saga
    0.40
    Activations Density 0.001%

    No Known Activations