© 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. 2920
    Prev
    Next
    INDEX
    Explanations

    you could

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

    things to know

    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
    uke
    0.43
     }_{\
    0.41
    హం
    0.41
    ulé
    0.40
    、“
    0.39
    রকম
    0.38
    丿
    0.38
     タン
    0.38
    スキン
    0.38
    POSITIVE LOGITS
     Utilization
    0.43
     utilization
    0.42
     কার্যত
    0.39
     utilized
    0.38
     Subsequent
    0.38
     Utilizing
    0.38
     Util
    0.37
     strains
    0.35
     points
    0.35
     whatsoever
    0.35
    Activations Density 0.142%

    No Known Activations