© 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. 17529
    Prev
    Next
    INDEX
    Explanations

    predicting future events

    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
     decolor
    0.59
     investig
    0.54
     integrand
    0.53
     ceg
    0.48
     digoxin
    0.48
    t
    0.48
     исследователь
    0.47
    uq
    0.47
     ciclos
    0.47
     immunohist
    0.46
    POSITIVE LOGITS
    धील
    0.42
     ASSEMBLY
    0.42
    密码
    0.41
    मताओं
    0.41
     MODELS
    0.40
    墀
    0.40
    沨
    0.40
    мер
    0.40
    rowData
    0.40
    Amy
    0.39
    Activations Density 0.002%

    No Known Activations