© 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. 193425
    Prev
    Next
    INDEX
    Explanations

    due to

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

    normal vs nuanced variation

    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
    螫
    0.54
     nœ
    0.53
     στι
    0.50
    니까
    0.50
     physiologique
    0.50
     orale
    0.49
    ið
    0.48
     ಈಗ
    0.48
    iiv
    0.47
     नु
    0.47
    POSITIVE LOGITS
     treasurer
    0.42
    ende
    0.41
    ར
    0.40
    aka
    0.40
     refinery
    0.40
    Scholar
    0.39
     popular
    0.39
     roles
    0.38
    成员
    0.38
    Port
    0.38
    Activations Density 0.001%

    No Known Activations