© 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. 965
    Prev
    Next
    INDEX
    Explanations

    why it works

    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
    </strong>
    1.91
    ↵
    1.66
    ↵↵
    1.54
    ’
    1.50
     of
    1.49
    ,
    1.44
    quarter
    1.41
    </b>
    1.39
    ini
    1.39
    ing
    1.38
    POSITIVE LOGITS
    ሠራ
    2.33
     tiež
    2.30
     nazy
    2.27
     požad
    2.20
     projeto
    2.19
    ግብ
    2.19
    ἂ
    2.19
     ràng
    2.17
     पूछता
    2.16
     problèmes
    2.15
    Activations Density 0.509%

    No Known Activations