© 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. 12246
    Prev
    Next
    INDEX
    Explanations

    always or again

    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
     тогда
    -1.11
    ního
    -1.08
     сначала
    -1.00
     począ
    -0.96
     initial
    -0.93
    zumaki
    -0.93
    utsu
    -0.93
     Katherine
    -0.91
     Initially
    -0.91
     discovery
    -0.89
    POSITIVE LOGITS
     always
    2.69
     again
    2.44
     sempre
    2.19
     toujours
    2.16
     всегда
    2.14
    今回も
    2.08
    always
    2.08
    Always
    2.06
     siempre
    1.95
     завжди
    1.89
    Activations Density 0.080%

    No Known Activations