© 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. 131054
    Prev
    Next
    INDEX
    Explanations

    company names and dates

    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
    Jeden
    -1.21
    genodigd
    -1.21
    Osob
    -1.15
     jak
    -1.13
     meager
    -1.13
     decenas
    -1.09
    Ꮞ
    -1.09
    ｖ
    -1.06
     "<
    -1.05
     مختلف
    -1.05
    POSITIVE LOGITS
    )
    1.27
    ;
    1.19
     giorgio
    1.05
     lorenzo
    1.02
    ).
    1.01
     indescri
    1.01
     herrera
    1.00
     those
    0.98
    );
    0.97
     mať
    0.97
    Activations Density 0.024%

    No Known Activations