© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12154
    Prev
    Next
    INDEX
    Explanations

    disasters and their impact

    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
    înt
    -1.10
    leftarrow
    -1.08
    --)
    -1.05
    鐽
    -1.04
    ;*/
    -1.02
     án
    -1.01
    iliares
    -0.99
     bestand
    -0.99
    ()]);
    -0.96
     sánh
    -0.96
    POSITIVE LOGITS
     affecting
    1.43
     affect
    1.27
     affects
    1.20
    Affect
    1.19
     Affecting
    1.16
     khiến
    1.15
    ทำให้
    1.15
    していない
    1.11
     باعث
    1.09
     has
    1.06
    Activations Density 0.045%

    No Known Activations