© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43694
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios and conditions

    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_31_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
     частини
    0.53
    Л
    0.50
    Quel
    0.46
     системи
    0.46
    실
    0.44
    Header
    0.44
    Ін
    0.44
    Formal
    0.43
     україн
    0.42
    Ф
    0.42
    POSITIVE LOGITS
     reverse
    0.52
     game
    0.52
     storage
    0.52
     story
    0.52
     descendant
    0.52
     revolver
    0.52
     survival
    0.51
     loot
    0.51
     trajectory
    0.49
     longevity
    0.49
    Activations Density 0.005%

    No Known Activations