© 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. 209594
    Prev
    Next
    INDEX
    Explanations

    latest feature

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

    if there's anything

    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
     ceded
    0.44
    不可以
    0.42
    徭
    0.41
     représenter
    0.39
     fiancée
    0.38
     inextric
    0.38
    .'%
    0.38
    表現
    0.38
     économiques
    0.38
    CONNECTED
    0.38
    POSITIVE LOGITS
    ee
    0.49
    ig
    0.49
    טי
    0.49
    ope
    0.48
    emple
    0.48
     प्रतिदिन
    0.47
    og
    0.47
    fly
    0.47
    ackle
    0.47
    ess
    0.46
    Activations Density 0.000%

    No Known Activations