© 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. 53457
    Prev
    Next
    INDEX
    Explanations

    releasing happiness

    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
     se
    0.47
    pping
    0.45
    u
    0.43
     tele
    0.43
    ila
    0.42
    uku
    0.42
    angling
    0.41
     unsub
    0.41
     o
    0.41
     manuscript
    0.41
    POSITIVE LOGITS
    Instead
    0.54
     ermög
    0.50
     invece
    0.48
     jaunâtre
    0.47
     associée
    0.46
    出色
    0.46
     gleiche
    0.46
    )।
    0.46
    代わりに
    0.45
    ใช
    0.44
    Activations Density 0.002%

    No Known Activations