© 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. 10-GEMMASCOPE-RES-131K
    7. 101193
    Prev
    Next
    INDEX
    Explanations

    master suite/bedroom

    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
     to
    -1.92
    が違う
    -1.52
     podían
    -1.49
     différents
    -1.48
     lanza
    -1.43
    different
    -1.42
    了一個
    -1.37
    indest
    -1.36
     refleja
    -1.36
    ppled
    -1.35
    POSITIVE LOGITS
    Etimología
    1.32
    Preparazione
    1.25
     globos
    1.24
     our
    1.23
     vort
    1.23
     litri
    1.23
     Songtext
    1.21
    podes
    1.20
     biss
    1.20
    Inhalation
    1.20
    Activations Density 0.020%

    No Known Activations