© 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. 65337
    Prev
    Next
    INDEX
    Explanations

    analytic followed by concept

    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
     Entdecken
    -0.97
     bringe
    -0.93
    GAN
    -0.91
     Entdecke
    -0.91
     alligator
    -0.91
     Jetzt
    -0.90
     antagonist
    -0.89
     Vielen
    -0.88
     Beide
    -0.88
    daisy
    -0.85
    POSITIVE LOGITS
    ity
    1.01
    x
    0.97
     services
    0.92
     expressions
    0.91
    ynthetic
    0.90
    D
    0.88
    F
    0.85
    Consider
    0.85
     continuation
    0.84
    One
    0.84
    Activations Density 0.022%

    No Known Activations