© 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. 5695
    Prev
    Next
    INDEX
    Explanations

    positive descriptors

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

    good, efficient, easy, well

    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
     begann
    0.49
     unsuccessfully
    0.48
     asteroids
    0.46
     queria
    0.45
    😖
    0.45
     nemesis
    0.44
     wollte
    0.43
     ontst
    0.43
     someday
    0.43
     죽
    0.43
    POSITIVE LOGITS
     excellently
    0.85
     ample
    0.73
     wonderfully
    0.73
     прекрасно
    0.71
     plenty
    0.70
     superbly
    0.70
    很好的
    0.69
    良好
    0.68
     отлично
    0.68
     beautifully
    0.67
    Activations Density 0.205%

    No Known Activations