© 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. 22-GEMMASCOPE-RES-131K
    7. 66123
    Prev
    Next
    INDEX
    Explanations

    every single

    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
     dagar
    -1.24
     їх
    -1.23
    　『
    -1.15
     their
    -1.14
     If
    -1.13
     verschill
    -1.13
     smör
    -1.12
    前回の
    -1.10
     when
    -1.08
     Often
    -1.07
    POSITIVE LOGITS
    every
    1.33
     ]
    1.23
     ss
    1.22
     IndexPath
    1.19
     </
    1.16
     metav
    1.16
     ผู้
    1.16
    j
    1.14
    /</
    1.14
    yan
    1.13
    Activations Density 0.000%

    No Known Activations