© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76527
    Prev
    Next
    INDEX
    Explanations

    cloning and copying

    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
    簒
    -0.81
    睺
    -0.81
     Polícia
    -0.79
     Depuis
    -0.77
    Виды
    -0.77
    inite
    -0.76
    
    -0.75
     странах
    -0.75
     hasn
    -0.75
     IANS
    -0.74
    POSITIVE LOGITS
     onto
    0.85
    except
    0.82
    expensive
    0.80
    bria
    0.79
     expensive
    0.76
    onto
    0.76
     Except
    0.76
     मह
    0.74
    Except
    0.74
    exclude
    0.74
    Activations Density 0.027%

    No Known Activations