© 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. 26006
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    scarpe
    -1.08
    ("")
    -1.05
     kebiasaan
    -0.99
     används
    -0.98
    אלה
    -0.98
    izarea
    -0.94
    inella
    -0.94
    garbage
    -0.93
     Tienen
    -0.93
    fche
    -0.93
    POSITIVE LOGITS
     you
    1.00
    」
    0.91
     trö
    0.89
     geb
    0.87
    　→
    0.85
    }
    0.85
     would
    0.84
    Но
    0.83
     bonita
    0.82
    </b>
    0.82
    Activations Density 0.034%

    No Known Activations