© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11647
    Prev
    Next
    INDEX
    Explanations

    editors in citations

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

    citations with years

    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_40_width_16k_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
     nau
    0.41
     असतात
    0.38
     निर्भर
    0.37
     Individual
    0.36
    Nau
    0.36
    Individual
    0.36
     indywidual
    0.36
    }>\
    0.36
     ◇
    0.35
    individual
    0.35
    POSITIVE LOGITS
     Retrieved
    0.83
     retrieval
    0.75
     retrieved
    0.69
     Retrieval
    0.66
     retrieve
    0.62
     retrieving
    0.62
     retriever
    0.62
     Retrieve
    0.57
     retrieves
    0.55
     Retriever
    0.55
    Activations Density 0.074%

    No Known Activations