© 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. 62736
    Prev
    Next
    INDEX
    Explanations

    largest classifications

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

    largest noun entities

    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
    三年
    0.50
    Yas
    0.46
     үчүн
    0.46
    高兴
    0.46
     বয়
    0.46
     kere
    0.45
     বয়
    0.43
    浔
    0.42
     yıll
    0.42
    迩
    0.42
    POSITIVE LOGITS
     largest
    1.04
    largest
    1.04
     Largest
    0.98
    Largest
    0.97
    世界上最大的
    0.84
     বৃহত্তম
    0.75
     крупней
    0.74
     규모
    0.73
    규모
    0.71
     größten
    0.68
    Activations Density 0.053%

    No Known Activations