© 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-65K
    7. 27030
    Prev
    Next
    INDEX
    Explanations

    explanations following punctuation

    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_65k_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
     і
    0.46
    ardom
    0.43
     оп
    0.41
     у
    0.41
    ରା
    0.41
     clos
    0.40
     среду
    0.39
     б
    0.38
    ccess
    0.38
    𝗵
    0.38
    POSITIVE LOGITS
     Eğ
    0.51
     Igual
    0.50
     resolución
    0.50
     soldado
    0.47
     compañía
    0.45
     සමා
    0.45
     imidazole
    0.45
     Encoder
    0.44
     copiar
    0.44
    培养
    0.43
    Activations Density 0.011%

    No Known Activations