© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58540
    Prev
    Next
    INDEX
    Explanations

    government agencies and organizations

    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_34/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
     wirklich
    -1.35
    __);
    -1.34
     {},
    -1.31
    ^{*},
    -1.24
     terkenal
    -1.24
    になるので
    -1.19
    becomes
    -1.18
     появля
    -1.17
    )));
    -1.16
    )},
    -1.14
    POSITIVE LOGITS
     said
    2.48
     recently
    2.28
     has
    2.28
     earlier
    1.77
     had
    1.70
     issued
    1.68
     says
    1.66
     yesterday
    1.66
     last
    1.59
     released
    1.55
    Activations Density 0.087%

    No Known Activations