© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32110
    Prev
    Next
    INDEX
    Explanations

    software license terms

    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
     Menü
    -0.82
     REPLIES
    -0.75
    öng
    -0.74
    edish
    -0.73
    ***********/
    -0.73
    }*/
    -0.72
     configurações
    -0.72
     Seer
    -0.71
     Pág
    -0.71
    :"-
    -0.71
    POSITIVE LOGITS
     Kare
    0.90
     EEA
    0.81
     WHO
    0.81
    Transitions
    0.81
    IPs
    0.79
     Cin
    0.78
    колов
    0.75
    øre
    0.75
     Cui
    0.75
     IDA
    0.75
    Activations Density 0.002%

    No Known Activations