© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6776
    Prev
    Next
    INDEX
    Explanations

    code and security systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    inder
    0.94
     ISS
    0.91
     kaps
    0.88
    ajt
    0.86
     KER
    0.83
    INDER
    0.82
     DIF
    0.81
    Ủ
    0.80
    llllllll
    0.79
     Api
    0.79
    POSITIVE LOGITS
     thefts
    0.85
     shaved
    0.82
    エンド
    0.81
     robberies
    0.79
     inexperienced
    0.79
     theft
    0.78
     delitos
    0.77
     blandt
    0.76
    初の
    0.75
     burglary
    0.75
    Activations Density 0.050%

    No Known Activations