© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 159929
    Prev
    Next
    INDEX
    Explanations

    verbs followed by adverbs or infinitives

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

    Resizing, allocation, and specific places

    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
    기
    0.51
    함
    0.50
    水
    0.50
    ိ
    0.49
    会
    0.47
    π
    0.47
    모
    0.46
    translate
    0.46
    대
    0.46
    j
    0.46
    POSITIVE LOGITS
     ប្រ
    0.55
     поста
    0.51
    MemoryWarning
    0.51
     automatiquement
    0.51
    SpecID
    0.51
     ใช่
    0.49
    aky
    0.49
    <unused2103>
    0.49
     വ്യക്തി
    0.49
    NgramModel
    0.49
    Activations Density 0.000%

    No Known Activations