© 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. 34-GEMMASCOPE-RES-131K
    7. 109815
    Prev
    Next
    INDEX
    Explanations

    out of

    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_34/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
     Debut
    -0.76
    Wymiary
    -0.75
    τσι
    -0.73
     fevereiro
    -0.70
     novembro
    -0.70
    onymus
    -0.69
    čni
    -0.69
    čna
    -0.68
     interni
    -0.68
    ඝ
    -0.66
    POSITIVE LOGITS
     out
    5.81
     Out
    4.03
    Out
    3.89
    OutOf
    3.42
    out
    3.08
     fuori
    2.75
     OUT
    2.66
     outta
    2.48
     fuera
    2.41
    OUT
    2.11
    Activations Density 0.108%

    No Known Activations