© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 9319
    Prev
    Next
    INDEX
    Explanations

    inventing fake facts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     느
    0.93
    AnyCPU
    0.91
     Dimension
    0.89
    ASSERT
    0.89
     Compressed
    0.87
     Longer
    0.86
     குற
    0.85
    apsing
    0.84
     Wich
    0.84
    OnClick
    0.84
    POSITIVE LOGITS
     views
    0.88
     followers
    0.86
     நன்க
    0.86
    K
    0.86
    yto
    0.85
    могою
    0.85
     অর্থ
    0.83
    kfollowers
    0.82
     donors
    0.82
     conos
    0.82
    Activations Density 0.070%

    No Known Activations