© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39758
    Prev
    Next
    INDEX
    Explanations

    consequences and thus

    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_22/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
    determine
    -1.09
    preferably
    -1.02
     capace
    -0.99
    🛸
    -0.96
     Waar
    -0.94
    continence
    -0.94
    حيث
    -0.93
     ite
    -0.93
     wond
    -0.92
     殼
    -0.92
    POSITIVE LOGITS
     this
    2.55
     thus
    2.17
     therefore
    1.64
     hence
    1.57
     Thus
    1.51
     also
    1.49
     so
    1.35
    这就是
    1.34
     thereby
    1.34
     then
    1.34
    Activations Density 0.021%

    No Known Activations