© 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. 22189
    Prev
    Next
    INDEX
    Explanations

    expressing opinions or views

    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
     in
    -3.55
     with
    -2.97
     on
    -2.91
     through
    -2.89
     for
    -2.88
     without
    -2.28
     at
    -2.23
     from
    -2.19
     across
    -2.06
     With
    -2.02
    POSITIVE LOGITS
    representing
    2.03
    eſ
    2.00
    すごく
    1.98
    considering
    1.98
     WHILE
    1.98
    蚨
    1.93
    
    1.91
    perhaps
    1.90
    currently
    1.89
    totally
    1.89
    Activations Density 0.008%

    No Known Activations