© 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. 12481
    Prev
    Next
    INDEX
    Explanations

    company and place 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
     moletom
    -1.43
    黉
    -1.38
    になりますが
    -1.36
     ratón
    -1.35
     Trabalho
    -1.29
     kompati
    -1.29
    应该
    -1.29
     Tamanho
    -1.28
     jugu
    -1.27
    Kde
    -1.27
    POSITIVE LOGITS
     with
    1.78
     at
    1.25
     has
    1.22
     after
    1.15
     in
    1.15
     add
    1.14
     also
    1.13
     there
    1.13
    set
    1.08
     from
    1.07
    Activations Density 0.018%

    No Known Activations