© 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. 7070
    Prev
    Next
    INDEX
    Explanations

    Kaunas

    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
     powiedzieć
    -0.85
     JOH
    -0.81
    नु
    -0.80
    événement
    -0.80
     Nid
    -0.79
     Huguen
    -0.78
     spind
    -0.77
    см
    -0.77
     getProperty
    -0.76
    áře
    -0.75
    POSITIVE LOGITS
    旁
    0.82
    bern
    0.79
    Service
    0.79
    ande
    0.77
    bgcolor
    0.75
     Service
    0.73
    StringBuffer
    0.71
    を書く
    0.71
    Pass
    0.70
     cenu
    0.70
    Activations Density 0.002%

    No Known Activations