© 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. 3292
    Prev
    Next
    INDEX
    Explanations

    material and criterion

    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
     natively
    2.16
     Forge
    2.10
    斎
    1.99
     overlays
    1.98
     liggen
    1.98
    libexec
    1.97
     Heli
    1.95
     crossings
    1.94
    ])$
    1.93
     Traverse
    1.93
    POSITIVE LOGITS
     naf
    1.11
    BlackElo
    0.93
    athione
    0.89
    적
    0.85
    ipient
    0.84
     kandid
    0.83
    CBN
    0.82
     vagas
    0.80
     memória
    0.79
     cholest
    0.78
    Activations Density 0.031%

    No Known Activations