© 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. 58216
    Prev
    Next
    INDEX
    Explanations

    outwardly directed

    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
     veille
    -0.69
    לים
    -0.69
     gereja
    -0.68
     pemimpin
    -0.68
    uetas
    -0.68
    Trevor
    -0.68
     Deadline
    -0.68
    vidad
    -0.68
     Minimize
    -0.67
     ineff
    -0.67
    POSITIVE LOGITS
     kit
    0.68
    стро
    0.67
    строить
    0.67
     conference
    0.66
     audio
    0.64
    Wireless
    0.63
    conference
    0.63
    CRYPTO
    0.62
     wireless
    0.62
     academic
    0.61
    Activations Density 0.088%

    No Known Activations