© 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. 66341
    Prev
    Next
    INDEX
    Explanations

    code and data context

    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
     bosques
    -1.26
     his
    -1.17
     edificios
    -1.10
     июля
    -1.09
     abstract
    -1.05
     apoy
    -1.02
     cozinha
    -1.01
     растение
    -1.00
     attachment
    -1.00
     mogelijk
    -0.99
    POSITIVE LOGITS
     toti
    1.14
    Moreover
    1.04
     simpat
    1.02
     skys
    1.02
    Além
    1.02
     similit
    1.01
     ordina
    0.99
     pseudos
    0.99
    Possui
    0.98
     スイッチ
    0.97
    Activations Density 0.002%

    No Known Activations