© 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. 74190
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes

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

    abstract concepts and multilingual

    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
     muito
    0.51
     дуже
    0.50
    entertainment
    0.50
     vrlo
    0.47
     );//
    0.47
     você
    0.47
     bardzo
    0.47
     çok
    0.46
     revitalization
    0.46
     很
    0.46
    POSITIVE LOGITS
     Guido
    0.44
     వాటి
    0.41
    gments
    0.41
     एजेंसियों
    0.40
     SESSION
    0.40
    辑
    0.39
     sådan
    0.39
    journ
    0.39
    炉
    0.39
    में
    0.38
    Activations Density 0.001%

    No Known Activations