© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68514
    Prev
    Next
    INDEX
    Explanations

    code attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kommentare
    -1.17
    tya
    -1.15
     作り方
    -1.15
     早餐
    -1.14
     harap
    -1.13
    wüns
    -1.10
     anecdotes
    -1.06
    ॉग
    -1.05
    ㎎
    -1.04
     Penyakit
    -1.02
    POSITIVE LOGITS
    之际
    1.21
     again
    1.19
    ?
    1.15
    之时
    1.05
     also
    1.03
    就可以了
    1.00
     dragging
    0.94
    ”
    0.92
    !
    0.91
     kolejny
    0.89
    Activations Density 0.018%

    No Known Activations