© 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. 37375
    Prev
    Next
    INDEX
    Explanations

    recruitment, arrests, chemistry, recall, study

    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
    ро
    0.39
     instructional
    0.38
    вної
    0.38
     иш
    0.38
    I
    0.38
    cing
    0.37
    ฏ
    0.37
     upcoming
    0.37
    ロ
    0.37
    ᡤ
    0.37
    POSITIVE LOGITS
     Sadly
    0.50
     havde
    0.47
     theseKeys
    0.47
     زمانی
    0.46
     genü
    0.45
     Sometimes
    0.44
     When
    0.44
    短短
    0.44
     manchmal
    0.44
     Millions
    0.43
    Activations Density 0.007%

    No Known Activations