© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13242
    Prev
    Next
    INDEX
    Explanations

    address data

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

    sorting lists and arrays

    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_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
    inos
    0.46
    iança
    0.46
    諜
    0.44
     welder
    0.42
    anians
    0.42
    pubmed
    0.42
     richiesta
    0.41
    iones
    0.41
     transferencia
    0.41
    agona
    0.41
    POSITIVE LOGITS
    Exec
    0.50
    क्‍
    0.48
    Continuing
    0.48
    ट
    0.48
     хра
    0.47
    хра
    0.46
     तारी
    0.46
    格納
    0.45
    भ
    0.45
    ----------
    0.45
    Activations Density 0.001%

    No Known Activations