© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31678
    Prev
    Next
    INDEX
    Explanations

    network ports and ips

    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
     客厅
    -1.00
     at
    -0.95
    ActivityResult
    -0.91
     pecado
    -0.89
     pharmacy
    -0.88
    嵩
    -0.85
    ustris
    -0.85
    CLUDING
    -0.83
    ˗
    -0.82
     написа
    -0.82
    POSITIVE LOGITS
     sekunder
    0.79
    Gabriela
    0.78
     Shiro
    0.78
    Monta
    0.77
    Shiro
    0.77
    ctie
    0.76
     gré
    0.76
     gne
    0.75
    izowane
    0.75
    Sono
    0.74
    Activations Density 0.022%

    No Known Activations