© 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. 32200
    Prev
    Next
    INDEX
    Explanations

    faculty member or adviser

    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
    kop
    -0.91
    ضير
    -0.90
     personalidades
    -0.83
    𝑄
    -0.82
     atitude
    -0.82
     periodistas
    -0.81
     mundiales
    -0.81
    umumkan
    -0.79
     funktioniert
    -0.79
    LINEAR
    -0.79
    POSITIVE LOGITS
     senate
    1.13
     member
    1.00
     Senate
    0.98
    чены
    0.93
    yyy
    0.85
     cloak
    0.84
    obiety
    0.82
    richment
    0.82
     lounge
    0.82
     tog
    0.82
    Activations Density 0.007%

    No Known Activations