© 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. 10-GEMMASCOPE-RES-131K
    7. 100214
    Prev
    Next
    INDEX
    Explanations

    meeting people and professionals

    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_10/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
    <strong>
    -1.57
    z
    -1.38
    et
    -1.26
    7
    -1.25
    2
    -1.23
     beiden
    -1.23
    rather
    -1.23
    j
    -1.22
    x
    -1.22
    right
    -1.22
    POSITIVE LOGITS
     through
    1.77
     dominar
    1.54
     destruir
    1.49
     conquistar
    1.49
     like
    1.48
     with
    1.47
     perdeu
    1.42
    鏵
    1.42
     dėl
    1.41
     disfru
    1.38
    Activations Density 0.038%

    No Known Activations