© 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. 31-GEMMASCOPE-2-RES-262K
    7. 24965
    Prev
    Next
    INDEX
    Explanations

    time estimations

    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
     DOOR
    0.43
     arXiv
    0.43
     iniciativa
    0.42
     عنہ
    0.40
    胝
    0.40
    ⊆
    0.40
     conducta
    0.39
    manam
    0.38
     Yale
    0.38
     WorldCat
    0.38
    POSITIVE LOGITS
    audio
    0.43
     heavyweight
    0.39
    pants
    0.38
    requis
    0.38
    ტ
    0.38
    ű
    0.38
    value
    0.38
    टे
    0.37
    ūs
    0.37
    Б
    0.37
    Activations Density 0.002%

    No Known Activations