© 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. 22-GEMMASCOPE-RES-131K
    7. 26970
    Prev
    Next
    INDEX
    Explanations

    must, should, continue, return

    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
     metais
    -0.92
     вообще
    -0.89
     actuality
    -0.81
     PROCEEDINGS
    -0.81
     useAuth
    -0.80
     serviceName
    -0.80
     없습니다
    -0.78
     lalu
    -0.78
    umentos
    -0.74
    osgi
    -0.74
    POSITIVE LOGITS
     it
    0.94
     should
    0.91
     return
    0.89
    continue
    0.87
    璟
    0.85
    should
    0.83
     will
    0.82
     interrogated
    0.82
    ERe
    0.80
    retour
    0.79
    Activations Density 0.056%

    No Known Activations