© 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. 73821
    Prev
    Next
    INDEX
    Explanations

    scan followed by various contexts

    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
     คือ
    -2.34
    Muchas
    -2.17
     funguje
    -2.16
    UNTAIN
    -2.08
    킁
    -2.06
     آنها
    -2.03
    媄
    -2.03
    隂
    -2.02
    ⁛
    -2.02
     Crear
    -1.98
    POSITIVE LOGITS
    ?
    3.30
    of
    2.33
    e
    2.28
     waar
    2.25
    z
    2.17
    in
    2.09
     reputable
    2.08
    !
    2.08
    able
    2.05
     haben
    2.05
    Activations Density 0.012%

    No Known Activations