© 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-262K
    7. 122938
    Prev
    Next
    INDEX
    Explanations

    verbs or prepositions after certain words

    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
    a
    0.54
    的
    0.48
     ambiente
    0.47
     está
    0.46
     localização
    0.45
     industria
    0.44
     القص
    0.44
    া
    0.44
     م
    0.44
     m
    0.43
    POSITIVE LOGITS
    enuine
    0.55
    nahi
    0.52
    ptives
    0.50
     waning
    0.50
    hty
    0.47
    ਧੀ
    0.47
    öld
    0.46
    umably
    0.46
    रावट
    0.46
    uret
    0.46
    Activations Density 0.000%

    No Known Activations