© 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. 991
    Prev
    Next
    INDEX
    Explanations

    digital pins

    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
     until
    -0.92
    hlander
    -0.91
     Helfer
    -0.84
    IonicModule
    -0.83
    tello
    -0.82
     sánchez
    -0.77
    textrm
    -0.77
    ன்று
    -0.77
    ié
    -0.76
    ਓ
    -0.76
    POSITIVE LOGITS
     pins
    0.91
     pin
    0.88
     Expressway
    0.82
    Brexit
    0.82
    getragen
    0.81
    Usb
    0.81
    ᾥ
    0.81
    pin
    0.81
     gewüns
    0.79
     JA
    0.77
    Activations Density 0.007%

    No Known Activations