© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50072
    Prev
    Next
    INDEX
    Explanations

    Ed followed by punctuation

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

    learning best styles

    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_31_width_262k_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
     interesantes
    0.48
     qualifiers
    0.43
    晟
    0.43
     schemas
    0.42
     environments
    0.42
     poderia
    0.42
     credentials
    0.42
    ၀
    0.41
     Subsidi
    0.40
    ੰਜਾਬ
    0.40
    POSITIVE LOGITS
     magaz
    0.45
     користу
    0.44
     ყველა
    0.44
     ის
    0.42
     визуа
    0.42
    ほか
    0.41
    拴
    0.41
     उड़
    0.41
     rozgry
    0.41
     त्रुट
    0.41
    Activations Density 0.000%

    No Known Activations