© 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. 6373
    Prev
    Next
    INDEX
    Explanations

    best and better practices

    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
     !=
    0.38
     zwar
    0.37
     допусти
    0.37
     falling
    0.35
     entityManager
    0.34
     Invalid
    0.34
     Difficult
    0.33
     ==>
    0.33
     ==
    0.33
     Everett
    0.33
    POSITIVE LOGITS
     suited
    0.94
    suited
    0.87
     behaved
    0.66
     equipped
    0.59
    behaved
    0.58
    equipped
    0.57
     versed
    0.54
    versed
    0.54
    liked
    0.53
    performing
    0.52
    Activations Density 0.044%

    No Known Activations