© 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. 13450
    Prev
    Next
    INDEX
    Explanations

    How can explain enhanced creativity

    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
     necessario
    0.49
    மில்லை
    0.48
    AX
    0.45
    s
    0.45
    ৬
    0.44
    WR
    0.43
     necessário
    0.43
     azione
    0.43
    ਾਕ
    0.42
     বললো
    0.42
    POSITIVE LOGITS
     entail
    0.49
     tenements
    0.44
    좆
    0.43
     grate
    0.42
     embezzlement
    0.42
     inland
    0.42
     bookkeeping
    0.41
     Seaside
    0.41
     lodges
    0.41
    quarters
    0.41
    Activations Density 0.002%

    No Known Activations