© 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. 40-GEMMASCOPE-2-RES-262K
    7. 120393
    Prev
    Next
    INDEX
    Explanations

    introduction of specific terms

    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_40_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
    glas
    0.42
     вечер
    0.39
    ENGE
    0.39
     wzgl
    0.38
    ЕВ
    0.38
    晚
    0.38
     folgen
    0.38
     వార్
    0.38
     частина
    0.38
    instruction
    0.37
    POSITIVE LOGITS
     mone
    0.43
     হাব
    0.42
     monop
    0.40
    κτή
    0.39
    ✭
    0.37
     صنا
    0.36
     griseo
    0.35
     gacche
    0.35
     monopole
    0.35
    貫
    0.35
    Activations Density 0.005%

    No Known Activations