© 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. 58225
    Prev
    Next
    INDEX
    Explanations

    set or get methods

    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
    癌症
    -1.19
    чил
    -1.13
     ofere
    -1.09
     ſhall
    -1.02
    »;
    -1.02
     confirme
    -1.01
     inſ
    -0.99
    ")));
    -0.99
    \"");
    -0.99
    warzys
    -0.96
    POSITIVE LOGITS
     that
    1.39
     generalmente
    1.20
     território
    1.03
     mało
    1.02
     gold
    1.00
    excellents
    0.96
     manchmal
    0.96
     utilizzato
    0.94
     direzione
    0.93
     genellikle
    0.93
    Activations Density 0.001%

    No Known Activations