© 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. 3296
    Prev
    Next
    INDEX
    Explanations

    list 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
    Not in Any Lists

    No Comments

    Negative Logits
    ën
    1.59
     overhaul
    1.53
     debugger
    1.52
     upheaval
    1.46
    olysis
    1.42
     recollection
    1.41
    ctomy
    1.41
     걱
    1.40
     maximization
    1.40
    づくり
    1.39
    POSITIVE LOGITS
     các
    1.84
    các
    1.58
    すべての
    1.51
     all
    1.49
     các
    1.47
    所有的
    1.46
     wszystkich
    1.46
    各类
    1.44
     усіх
    1.41
    Các
    1.39
    Activations Density 0.364%

    No Known Activations