© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99582
    Prev
    Next
    INDEX
    Explanations

    other entities / parties

    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
     tomates
    -1.16
    人家
    -1.13
     ondes
    -1.09
    賸
    -1.02
    Guys
    -1.01
    女儿
    -0.98
     rente
    -0.98
    のもの
    -0.96
    opie
    -0.96
     frango
    -0.94
    POSITIVE LOGITS
     other
    2.45
     fellow
    1.93
    other
    1.74
     peers
    1.59
    他の
    1.45
    Other
    1.37
     colleagues
    1.37
     Other
    1.37
     government
    1.34
     otros
    1.34
    Activations Density 0.073%

    No Known Activations