© 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. 8736
    Prev
    Next
    INDEX
    Explanations

    This is

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

    this is

    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
     fleste
    0.42
     meeste
    0.41
    しています
    0.41
    鑾
    0.40
     Familia
    0.39
     اپنا
    0.39
    これまで
    0.39
    鯽
    0.38
     jakim
    0.38
    majority
    0.38
    POSITIVE LOGITS
     week
    0.75
    week
    0.69
     year
    0.65
    morning
    0.65
     happens
    0.63
     konuda
    0.63
     month
    0.63
     isn
    0.58
     году
    0.58
     guy
    0.58
    Activations Density 0.006%

    No Known Activations