© 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. 137385
    Prev
    Next
    INDEX
    Explanations

    weekly and daily events

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

    transformation, signal, system, relationship, studies

    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
    是个
    0.51
     принад
    0.47
    ග්
    0.47
    нду
    0.46
     sowohl
    0.43
    胝
    0.43
    夼
    0.43
    诒
    0.42
    ୌ
    0.42
     सीटेट
    0.42
    POSITIVE LOGITS
     verb
    0.44
     réaction
    0.42
     Unidos
    0.42
     ulei
    0.40
     reaction
    0.39
     rời
    0.38
     reacts
    0.38
     rested
    0.38
     बलि
    0.38
     fleeing
    0.37
    Activations Density 0.002%

    No Known Activations