© 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. 10-GEMMASCOPE-RES-131K
    7. 535
    Prev
    Next
    INDEX
    Explanations

    persuade

    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_10/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
     è
    -2.77
    ]
    -2.72
     *
    -2.70
     entr
    -2.58
     )
    -2.52
     pero
    -2.48
     But
    -2.45
     shows
    -2.44
     â
    -2.44
     может
    -2.34
    POSITIVE LOGITS
    了
    2.41
    ↵↵
    2.41
     内衣
    2.38
    屨
    2.31
    猡
    2.30
    ޏ
    2.27
    olate
    2.25
     représenter
    2.23
    蘩
    2.19
     lezen
    2.17
    Activations Density 0.003%

    No Known Activations