© 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. 53-GEMMASCOPE-2-RES-65K
    7. 3680
    Prev
    Next
    INDEX
    Explanations

    following closing punctuation

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

    emphasized words

    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
    ,</
    0.45
    ,?
    0.43
    ,}
    0.43
    ,\\
    0.42
    ,/
    0.40
    .//
    0.40
    ,__
    0.40
    .&
    0.39
    ,
    0.38
    ,=
    0.38
    POSITIVE LOGITS
    
    0.59
    এর
    0.59
     नामक
    0.59
    are
    0.54
    which
    0.53
    nın
    0.52
    who
    0.52
    suggest
    0.50
    ️
    0.50
    says
    0.49
    Activations Density 0.464%

    No Known Activations