© 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. 705
    Prev
    Next
    INDEX
    Explanations

    lectin lectures intellect

    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
    на
    -2.72
    ed
    -2.61
    ist
    -2.44
    ‘
    -2.33
    ization
    -2.31
    ”
    -2.28
     curtail
    -2.09
      
    -2.08
     mehrere
    -2.06
     неё
    -2.06
    POSITIVE LOGITS
    
    3.05
    pecabe
    2.67
    sandalia
    2.58
    犼
    2.56
    咴
    2.47
    赑
    2.44
    䛗
    2.44
    鉿
    2.42
    鷙
    2.39
     The
    2.38
    Activations Density 0.005%

    No Known Activations