© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 120659
    Prev
    Next
    INDEX
    Explanations

    annotation/decorator

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Assertions
    0.50
     assertTrue
    0.49
     assertions
    0.46
     Calcul
    0.45
    Assert
    0.43
    ባቸው
    0.42
     assert
    0.42
    釹
    0.42
     Assert
    0.42
     assertFalse
    0.42
    POSITIVE LOGITS
     reunion
    0.42
     سبق
    0.42
    uses
    0.40
     speeding
    0.40
     Vietnam
    0.38
     reunited
    0.37
    mailing
    0.37
     humidity
    0.37
     sped
    0.37
    och
    0.36
    Activations Density 0.002%

    No Known Activations