© 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. 113440
    Prev
    Next
    INDEX
    Explanations

    Marlene, Pret, Specifies, Serum, Father

    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
     größer
    -1.70
     sordid
    -1.63
     zwanzig
    -1.58
     großer
    -1.53
    ti
    -1.50
     écouter
    -1.49
      
    -1.48
     jenen
    -1.45
     lind
    -1.44
     gestern
    -1.44
    POSITIVE LOGITS
     OGSÅ
    1.84
     安心
    1.81
     psiqui
    1.59
     był
    1.56
    resten
    1.55
     всѣ
    1.52
     mentales
    1.49
    𝙧
    1.48
     apó
    1.47
     ofertas
    1.45
    Activations Density 0.000%

    No Known Activations