© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7380
    Prev
    Next
    INDEX
    Explanations

    the building block

    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
     பண்ப
    0.98
    두
    0.94
    ме
    0.93
    信息的
    0.91
    การณ์
    0.89
    鑑
    0.87
    փ
    0.86
    俩
    0.86
     두
    0.84
    信息
    0.83
    POSITIVE LOGITS
    iagnosed
    1.04
    oubtedly
    0.98
    efeated
    0.96
     schließlich
    0.89
     Hadid
    0.88
    imin
    0.87
     tepat
    0.86
     der
    0.84
    ulatus
    0.84
     Cip
    0.82
    Activations Density 0.036%

    No Known Activations