© 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. 103133
    Prev
    Next
    INDEX
    Explanations

    static IP address

    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
    wine
    -0.78
    碌
    -0.76
     egiten
    -0.74
    狸
    -0.74
    Tooth
    -0.74
     повседнев
    -0.73
    elec
    -0.71
    筒
    -0.70
    MouseEvent
    -0.69
    レード
    -0.69
    POSITIVE LOGITS
     IP
    4.41
     ip
    3.47
    IP
    3.39
     IPs
    3.02
    ip
    2.86
     Ip
    2.81
    Ip
    2.70
    IPAddress
    2.63
     IPv
    2.34
    IpAddress
    2.33
    Activations Density 0.115%

    No Known Activations