© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 217023
    Prev
    Next
    INDEX
    Explanations

    period or common words

    np_acts-logits-general · gemini-2.5-flash-lite

    Combinations, houses, adolescents, une, Returns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Пари
    0.49
    氖
    0.47
    ยนต์
    0.46
    鍱
    0.44
     Sonntag
    0.43
     కమి
    0.43
     פס
    0.42
     Face
    0.42
     Și
    0.41
     Parlement
    0.41
    POSITIVE LOGITS
    educational
    0.54
    area
    0.53
    wider
    0.53
    edu
    0.52
    ugly
    0.52
    똘
    0.52
    embl
    0.51
    १८४
    0.49
    ajem
    0.49
     Encourage
    0.48
    Activations Density 0.000%

    No Known Activations