© 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. 31-GEMMASCOPE-2-RES-16K
    7. 16311
    Prev
    Next
    INDEX
    Explanations

    cabins manufactures mansions

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

    image descriptions

    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
    戙
    0.45
    :'',
    0.41
    🪙
    0.40
     प
    0.40
    顶
    0.39
    rika
    0.38
     etiqueta
    0.38
    เรา
    0.37
    reste
    0.37
     क्ष
    0.37
    POSITIVE LOGITS
     azonban
    0.40
     yourself
    0.37
     criminals
    0.37
     이때
    0.36
     murderous
    0.36
    婉
    0.35
     mortality
    0.35
     cabins
    0.35
     manufactures
    0.35
     mansions
    0.35
    Activations Density 0.368%

    No Known Activations