© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 41321
    Prev
    Next
    INDEX
    Explanations

    snowflakes and their conditions

    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
    ριθ
    0.55
    рук
    0.49
    िकल
    0.47
    咟
    0.47
     recordemos
    0.46
     promul
    0.44
     বাঙালী
    0.43
     cien
    0.43
     hatal
    0.43
     plasmids
    0.43
    POSITIVE LOGITS
    disconnected
    0.52
    key
    0.48
    disconnect
    0.47
    €
    0.46
     contingent
    0.45
    لی
    0.44
    OLF
    0.44
    ・・・
    0.43
    RefreshToken
    0.43
     is
    0.43
    Activations Density 0.003%

    No Known Activations