© 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. 49999
    Prev
    Next
    INDEX
    Explanations

    entry, permission, licensed, electronic

    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
    Stuttgart
    -0.82
     fecund
    -0.80
    が現
    -0.75
     Bhattach
    -0.74
     Metal
    -0.74
     väg
    -0.73
     ಜ
    -0.71
     ewigen
    -0.71
     christlichen
    -0.71
    Krishna
    -0.71
    POSITIVE LOGITS
    bukkit
    1.26
     handel
    0.81
     Bung
    0.79
    总是
    0.78
    Flags
    0.78
    beau
    0.77
    urek
    0.77
    AddWithValue
    0.77
     suche
    0.76
    nora
    0.76
    Activations Density 0.018%

    No Known Activations