© 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. 170224
    Prev
    Next
    INDEX
    Explanations

    potential target

    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
    alia
    0.45
     Tolkien
    0.43
    alista
    0.41
    TikTok
    0.40
    agian
    0.39
    racial
    0.39
     controversies
    0.38
    猕
    0.38
     остав
    0.38
     सत्तार
    0.38
    POSITIVE LOGITS
     bracket
    0.46
     suppliers
    0.44
     percentage
    0.43
     gearbox
    0.43
     storage
    0.41
     metric
    0.40
     footpath
    0.40
     cellar
    0.40
     football
    0.40
     point
    0.39
    Activations Density 0.009%

    No Known Activations