© 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. 17686
    Prev
    Next
    INDEX
    Explanations

    brands, blend, full, glove, TOP, cause, button, fiction

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

    numbers and code structures

    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
     eer
    0.47
    again
    0.45
    Ꮂ
    0.42
     vastly
    0.42
    Rồi
    0.41
    Again
    0.41
    روع
    0.40
    Jr
    0.39
     wiederum
    0.38
     luxe
    0.38
    POSITIVE LOGITS
     â
    0.58
     –
    0.57
    ↵↵↵↵
    0.51
     ``
    0.51
    …
    0.50
     XNUMX
    0.49
     Ã
    0.47
     "
    0.47
     …
    0.47
    ↵↵↵
    0.46
    Activations Density 0.147%

    No Known Activations