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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12354
    Prev
    Next
    INDEX
    Explanations

    Reuters reports

    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
     nggak
    -1.20
     enggak
    -1.08
     collega
    -1.07
    Whereas
    -1.04
    ५
    -1.01
     romantis
    -1.00
    '],$
    -0.99
    Incident
    -0.98
    Wymiary
    -0.97
     włosów
    -0.96
    POSITIVE LOGITS
    Reuters
    1.51
     Reuters
    1.50
    reuters
    1.35
     dijo
    1.30
    REUTERS
    1.22
     https
    1.19
     said
    1.19
    https
    1.16
     anx
    1.16
    rieu
    1.12
    Activations Density 0.174%

    No Known Activations