© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66803
    Prev
    Next
    INDEX
    Explanations

    don't have to be

    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
     rather
    -0.97
     ähnliche
    -0.96
    would
    -0.95
    cus
    -0.94
    ister
    -0.94
     sportage
    -0.93
    rather
    -0.92
     would
    -0.91
    amental
    -0.90
    ostante
    -0.90
    POSITIVE LOGITS
     necessarily
    1.63
     necesariamente
    1.23
     обязательно
    1.06
    tionnaire
    1.05
     anymore
    1.00
     necessariamente
    1.00
     "'";
    1.00
     to
    0.94
     olmak
    0.92
    necessarily
    0.91
    Activations Density 0.026%

    No Known Activations