© 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. 1141
    Prev
    Next
    INDEX
    Explanations

    on top or inside

    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
    께
    -0.83
     junto
    -0.80
     dalam
    -0.79
    Dans
    -0.78
    $.
    -0.76
    vā
    -0.76
     thiệu
    -0.72
     при
    -0.71
    Inject
    -0.71
    offe
    -0.70
    POSITIVE LOGITS
     on
    2.81
     On
    1.48
    On
    1.24
    OnThe
    1.20
     сверху
    1.11
    onthe
    1.06
     internally
    1.02
     På
    0.99
     outside
    0.94
     externally
    0.94
    Activations Density 0.029%

    No Known Activations