© 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. 60419
    Prev
    Next
    INDEX
    Explanations

    phone brands and models

    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
    Dziękuję
    -0.88
    </tr>
    -0.87
    roslav
    -0.87
     Kompon
    -0.82
    Polecam
    -0.81
    Kiedy
    -0.80
    Bardzo
    -0.79
    鐐
    -0.78
     decoracion
    -0.75
     odası
    -0.75
    POSITIVE LOGITS
     note
    1.15
     NOTE
    1.13
     Note
    1.12
     phone
    1.07
     phones
    1.05
    note
    1.03
     MIX
    1.02
     pro
    1.00
     Pro
    0.98
    NOTE
    0.93
    Activations Density 0.010%

    No Known Activations