Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11621
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.08
     (
    -1.04
     &
    -0.92
    люб
    -0.91
     on
    -0.88
     discharge
    -0.85
     –
    -0.84
           
    -0.84
     od
    -0.84
    ,-
    -0.83
    POSITIVE LOGITS
     dizaines
    1.16
     adresses
    1.05
     prachtige
    1.05
    纐
    1.03
     ebenso
    1.03
    fantastic
    1.03
     สี
    1.00
     véhicule
    0.98
     Dazu
    0.98
    人和
    0.96
    Activations Density 0.063%

    No Known Activations