© 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. 34-GEMMASCOPE-RES-131K
    7. 98216
    Prev
    Next
    INDEX
    Explanations

    millions of years

    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
    :
    -1.15
    ;
    -1.08
     \&
    -1.05
    来週
    -1.02
    とおり
    -1.02
    ),
    -0.99
     our
    -0.99
    ;
    -0.98
     Here
    -0.97
    ();
    -0.96
    POSITIVE LOGITS
     alemanes
    1.24
    などが
    1.20
     ulike
    1.08
    МС
    1.08
     kjem
    1.07
     utilisons
    1.07
    дости
    1.06
     minimale
    1.05
     lachen
    1.04
     klim
    1.04
    Activations Density 0.088%

    No Known Activations