© 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. 40101
    Prev
    Next
    INDEX
    Explanations

    roles and positions

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

    MBA, leadership, Membrane, Excel, access, training, Intent

    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
    袴
    0.48
    และ
    0.44
     लगवा
    0.42
    Сейчас
    0.41
    orrh
    0.41
    ucher
    0.41
    ጅም
    0.40
    oupe
    0.40
    驄
    0.40
    獭
    0.39
    POSITIVE LOGITS
     culinary
    0.46
    ↵
    0.44
     chefs
    0.43
     departing
    0.43
     tucked
    0.42
     değerli
    0.42
     düzenlenen
    0.42
     differently
    0.42
     delicacies
    0.42
     dietro
    0.42
    Activations Density 0.001%

    No Known Activations