© 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. 4240
    Prev
    Next
    INDEX
    Explanations

    implied probability

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

    multiple, severe ways

    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
     —
    0.46
     Term
    0.40
    👨
    0.40
     Geometry
    0.39
     «
    0.38
     _
    0.38
    🏊
    0.38
     _:
    0.38
    ‼️
    0.38
    ❗️
    0.37
    POSITIVE LOGITS
    லோச
    0.40
    かなり
    0.40
    Vorlage
    0.39
    closeup
    0.38
    ෙක්
    0.38
    ubicin
    0.38
     copyspace
    0.38
    arounds
    0.37
    öst
    0.37
    ihe
    0.37
    Activations Density 0.300%

    No Known Activations