© 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. 71287
    Prev
    Next
    INDEX
    Explanations

    conducted by

    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
    й
    -1.09
     conç
    -1.08
    indade
    -1.07
     множество
    -1.05
     иногда
    -1.05
    ך
    -1.02
    ская
    -1.01
     déploy
    -1.01
     souvent
    -1.00
     wither
    -1.00
    POSITIVE LOGITS
    бочки
    1.27
    }{$
    1.13
     „
    1.11
     dasselbe
    1.05
     regione
    1.04
    ῾
    1.04
     “
    0.99
     alfab
    0.98
    duino
    0.95
    vertising
    0.95
    Activations Density 0.090%

    No Known Activations