© 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. 16732
    Prev
    Next
    INDEX
    Explanations

    block encryption, healing links

    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
     זמן
    0.53
     શબ્
    0.51
     ხელისუფლების
    0.47
     शब्दा
    0.47
     एक्सप्लेन
    0.46
     довольно
    0.46
    媜
    0.46
     кусо
    0.45
     небольшой
    0.45
    墺
    0.45
    POSITIVE LOGITS
     and
    0.50
     requires
    0.48
    https
    0.45
     interactions
    0.45
     links
    0.45
     patients
    0.44
    healing
    0.43
     https
    0.43
     mobile
    0.43
     athletes
    0.43
    Activations Density 0.009%

    No Known Activations