© 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. 98194
    Prev
    Next
    INDEX
    Explanations

    Fanning v. Fanning

    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
     of
    -1.29
     podremos
    -1.09
    也要
    -1.06
    oggi
    -1.06
    粑
    -1.01
     الق
    -0.97
     alberga
    -0.97
    autorité
    -0.96
     that
    -0.96
    océ
    -0.95
    POSITIVE LOGITS
     ursprünglichen
    1.13
    以上
    0.98
    みてください
    0.96
    見到
    0.94
     ewigen
    0.94
    breakpoint
    0.93
     gesuchten
    0.93
    幾乎
    0.93
     vorigen
    0.92
     NOTHING
    0.92
    Activations Density 0.004%

    No Known Activations