© 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. 12245
    Prev
    Next
    INDEX
    Explanations

    names and family relationships

    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
    tive
    -1.00
     pourraient
    -0.98
    ervant
    -0.95
    dium
    -0.92
    halen
    -0.90
    MLElement
    -0.89
    =!
    -0.88
    titu
    -0.88
     deras
    -0.88
    uchy
    -0.87
    POSITIVE LOGITS
    Among
    1.16
     Mehrheit
    1.06
    моби
    1.04
     Erkrank
    1.00
    woj
    1.00
     riun
    0.99
     betreffenden
    0.98
     erweiterten
    0.96
    وقت
    0.95
    elesaikan
    0.94
    Activations Density 0.000%

    No Known Activations