© 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. 53-GEMMASCOPE-2-RES-65K
    7. 981
    Prev
    Next
    INDEX
    Explanations

    the town, simple actions

    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_53_width_65k_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
    …]
    0.35
    ']).
    0.34
    𝟏
    0.31
    जीर
    0.31
    implicitly
    0.30
    𝐦
    0.30
    ultima
    0.30
     रखकर
    0.29
    這一
    0.29
    သမ
    0.29
    POSITIVE LOGITS
    ਼
    0.38
     TextArea
    0.36
    =""
    0.35
    ˌ
    0.34
    뵙
    0.34
     ..............
    0.34
     ,"
    0.33
     "",
    0.32
     furtherance
    0.32
    ................
    0.32
    Activations Density 0.559%

    No Known Activations