© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1027
    Prev
    Next
    INDEX
    Explanations

    introducing examples or code

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

    the Russian word "вот" (meaning "here" or "look") and similar discourse markers in various languages.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    one
    -1.38
     Other
    -1.31
    first
    -1.30
    not
    -1.30
    着一
    -1.27
    ES
    -1.25
    key
    -1.25
    if
    -1.25
     up
    -1.24
     another
    -1.24
    POSITIVE LOGITS
    íte
    1.52
     serveur
    1.29
     儿童
    1.29
    |}{}
    1.28
    ducati
    1.27
    ॣ
    1.27
    🌛
    1.26
     könnte
    1.26
    这些人
    1.25
     sollte
    1.24
    Activations Density 0.007%

    No Known Activations