© 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. 27126
    Prev
    Next
    INDEX
    Explanations

    design studio names

    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
    そして
    -1.11
    その
    -1.09
     который
    -1.01
    は
    -1.01
     senhora
    -0.99
    Präsident
    -0.98
     cantora
    -0.96
     precisa
    -0.96
     praia
    -0.95
     difficile
    -0.94
    POSITIVE LOGITS
    ()}>
    1.30
     sufrir
    1.12
    jątk
    1.06
     absence
    1.05
     każ
    1.04
     cantidades
    1.03
     umgeben
    1.03
    seded
    1.02
     verdaderamente
    1.01
    instead
    0.99
    Activations Density 0.001%

    No Known Activations