© 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. 7639
    Prev
    Next
    INDEX
    Explanations

    expected, anticipated, or intended outcomes

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

    as requested or expected

    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
     chấp
    0.49
    认
    0.45
     thromb
    0.44
     οποίο
    0.43
    觉得自己
    0.43
     करणार
    0.43
     форме
    0.43
     hasonló
    0.43
    ﻚ
    0.43
    郏
    0.42
    POSITIVE LOGITS
     originally
    0.55
     expected
    0.55
    according
    0.54
     according
    0.53
     erwart
    0.52
     Expected
    0.51
     erwartet
    0.51
    লে
    0.50
    on
    0.50
    expected
    0.49
    Activations Density 0.032%

    No Known Activations