© 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. 860
    Prev
    Next
    INDEX
    Explanations

    technical qualifiers + specific nouns

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

    hierarchical, categorical, blocking, IV

    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
     foodie
    0.44
     सम्बंधित
    0.43
     hảo
    0.43
     সংশ্লিষ্ট
    0.43
     empresario
    0.42
     booze
    0.41
    觎
    0.41
     badass
    0.41
     इसी
    0.41
     comida
    0.41
    POSITIVE LOGITS
    ness
    0.68
    ity
    0.67
     $(<
    0.61
     ones
    0.61
    ly
    0.54
     mode
    0.54
     ("
    0.53
    ITY
    0.53
     versus
    0.53
     („
    0.52
    Activations Density 0.478%

    No Known Activations