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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14653
    Prev
    Next
    INDEX
    Explanations

    Lifeline: crisis contact details

    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_7_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
     teinture
    2.13
     appena
    2.08
     étapes
    2.02
     blushed
    1.97
     órgãos
    1.95
     cheery
    1.95
    蕖
    1.94
     dutiful
    1.94
     arreg
    1.93
    恂
    1.90
    POSITIVE LOGITS
    rangle
    1.63
    VA
    1.55
    Ar
    1.43
    Par
    1.43
    statistical
    1.42
     Dar
    1.41
    Va
    1.41
     Par
    1.38
    ro
    1.37
    Review
    1.36
    Activations Density 0.002%

    No Known Activations