© 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. 3188
    Prev
    Next
    INDEX
    Explanations

    amounts of

    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
     vapors
    3.60
    俺
    3.41
     flavors
    3.00
     flavor
    2.87
     Nebraska
    2.85
     analogs
    2.82
     colors
    2.80
     Marquette
    2.79
     jewelry
    2.77
     armor
    2.76
    POSITIVE LOGITS
    personalised
    3.72
     بى
    3.50
     generalised
    3.49
     minimising
    3.47
     maximising
    3.47
     £
    3.47
     recognises
    3.44
     التى
    3.44
     centralised
    3.43
     realised
    3.39
    Activations Density 0.047%

    No Known Activations