© 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. 217224
    Prev
    Next
    INDEX
    Explanations

    local real estate

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

    steps onto

    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
    てる
    0.44
     Grape
    0.42
    iedz
    0.42
     বস
    0.41
    otene
    0.40
    োদ
    0.39
    桿
    0.39
    訛
    0.39
     가는
    0.39
     ascending
    0.39
    POSITIVE LOGITS
     zusätzliche
    0.47
     dodat
    0.46
     zusätz
    0.45
     liệt
    0.45
     supplémentaires
    0.43
     zusätzlichen
    0.43
     disminución
    0.43
     improperly
    0.42
    க
    0.42
     posteriormente
    0.42
    Activations Density 0.002%

    No Known Activations