© 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-16K
    7. 12102
    Prev
    Next
    INDEX
    Explanations

    limousine and party bus rental

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

    drive under the influence

    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_16k_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
    बद्ध
    0.45
    🗓
    0.45
    Incident
    0.44
    organizations
    0.44
    Organizations
    0.41
    Tian
    0.41
    लाश
    0.41
    ख्य
    0.40
    тет
    0.40
    ्ड
    0.39
    POSITIVE LOGITS
     세율
    0.49
     fmt
    0.44
     美
    0.44
     hurried
    0.44
    ギリス
    0.43
     ill
    0.42
     peux
    0.41
    しないで
    0.41
     പഴയ
    0.41
     centrifugal
    0.41
    Activations Density 0.016%

    No Known Activations