© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47469
    Prev
    Next
    INDEX
    Explanations

    end of sentence, official titles

    np_acts-logits-general · gemini-2.5-flash-lite

    officials and representatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     รู้
    0.41
    ногда
    0.40
    睁
    0.40
     cù
    0.40
     lego
    0.40
     терпе
    0.40
    風呂
    0.39
    😵
    0.39
     cảm
    0.38
     পরেও
    0.38
    POSITIVE LOGITS
    Director
    0.45
     Director
    0.45
    Commissioner
    0.44
    Commiss
    0.44
     Commissioner
    0.43
    added
    0.42
    Mayor
    0.42
    ហ៊ុន
    0.42
     وزير
    0.41
    Minister
    0.41
    Activations Density 0.017%

    No Known Activations