© 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. 109674
    Prev
    Next
    INDEX
    Explanations

    hiring positions and classifications

    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
     Loreto
    -0.85
    ਲਾ
    -0.80
     Nieuwe
    -0.74
    彼らの
    -0.73
     ادبی
    -0.72
     Honduras
    -0.70
    Quack
    -0.69
     emm
    -0.69
     És
    -0.69
    シンプル
    -0.69
    POSITIVE LOGITS
     classification
    1.13
    competitive
    1.00
     competitive
    0.92
     position
    0.92
     конкур
    0.90
     classifications
    0.90
     positions
    0.89
     classified
    0.86
     promotional
    0.84
    classification
    0.84
    Activations Density 0.016%

    No Known Activations