© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202973
    Prev
    Next
    INDEX
    Explanations

    performs, adds, is

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

    even if

    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
     spoon
    0.44
    (()
    0.43
     to
    0.42
     uniform
    0.40
    匙
    0.40
     warmed
    0.40
    (&
    0.39
     centred
    0.39
    pressure
    0.39
    正
    0.39
    POSITIVE LOGITS
     જન્મદિવસ
    0.55
     นาที
    0.52
    મેન્ટ
    0.50
    ͒
    0.50
     Idiot
    0.50
     मोटर्स
    0.50
     लेट्स
    0.50
     Hadoop
    0.50
     रद्द
    0.49
     दिरहम
    0.49
    Activations Density 0.001%

    No Known Activations