© 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. 21807
    Prev
    Next
    INDEX
    Explanations

    subject or Re:

    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
     kepada
    0.58
    面向
    0.51
    ให้กับ
    0.45
    对着
    0.45
     إلى
    0.45
     към
    0.45
    向
    0.44
     الى
    0.44
     Demographic
    0.43
     向
    0.43
    POSITIVE LOGITS
     via
    0.42
     SUBJECT
    0.41
     doughnuts
    0.40
    ักษ
    0.40
     통해서
    0.39
    ondi
    0.39
     gjennom
    0.39
     kautta
    0.39
     subiect
    0.38
    ᕕ
    0.38
    Activations Density 0.004%

    No Known Activations