© 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. 14632
    Prev
    Next
    INDEX
    Explanations

    knowledge and awareness that

    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
     but
    -1.81
    玊
    -1.46
     henvisninger
    -1.42
     grabación
    -1.38
     jika
    -1.38
     homicidio
    -1.36
    ३
    -1.35
     Prozent
    -1.34
     supervivencia
    -1.34
    鸶
    -1.33
    POSITIVE LOGITS
     that
    2.11
    there
    1.57
    Although
    1.50
    以及
    1.48
    although
    1.38
     intere
    1.30
    Conseils
    1.30
    Maybe
    1.30
     there
    1.28
    (￣
    1.28
    Activations Density 0.025%

    No Known Activations