© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164907
    Prev
    Next
    INDEX
    Explanations

    modal verbs/auxiliary verbs

    np_acts-logits-general · gemini-2.5-flash-lite

    avoiding vague terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     บน
    0.50
    บน
    0.48
    adium
    0.46
     ชอบ
    0.45
    ≐
    0.45
    adev
    0.44
    جلس
    0.44
     그죠
    0.44
    Ᏺ
    0.44
     الاس
    0.44
    POSITIVE LOGITS
    的模型
    0.46
     solitary
    0.43
     incubating
    0.43
     mời
    0.42
     architectures
    0.42
     ballast
    0.41
     spiking
    0.41
     namanya
    0.41
     sullen
    0.40
     Meng
    0.40
    Activations Density 0.001%

    No Known Activations