© 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. 77104
    Prev
    Next
    INDEX
    Explanations

    printing workflow and RIPs

    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
     angel
    -0.83
     Фе
    -0.82
     lệ
    -0.81
    Angel
    -0.79
    Shin
    -0.79
     Angel
    -0.77
     Raphael
    -0.77
    Responsive
    -0.77
     Shin
    -0.75
     Испании
    -0.75
    POSITIVE LOGITS
     RIP
    1.47
     imposition
    1.26
    RIP
    1.13
     Quark
    1.03
    Quark
    0.98
     workflow
    0.94
     Pref
    0.92
    rip
    0.89
     rip
    0.86
     Rip
    0.86
    Activations Density 0.053%

    No Known Activations