© 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. 151056
    Prev
    Next
    INDEX
    Explanations

    venture, drill, profile

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

    investment, visiting, involves

    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
    ۹
    0.49
     глю
    0.43
    ry
    0.42
    rogens
    0.42
     ਦਵਾਈ
    0.42
    day
    0.41
    ⵓ
    0.41
    嬙
    0.41
    telefono
    0.40
     artères
    0.40
    POSITIVE LOGITS
     eureka
    0.48
     পদ্ধতির
    0.46
    Geschichte
    0.45
    (
    0.44
    榕
    0.44
     Grü
    0.44
     Cách
    0.44
     doi
    0.43
     Jawaharlal
    0.42
     alebo
    0.42
    Activations Density 0.000%

    No Known Activations