© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14605
    Prev
    Next
    INDEX
    Explanations

    conditions and details

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

    governing rules and limitations

    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_16k_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
     комп
    0.42
     Swezey
    0.42
     vị
    0.41
    闶
    0.41
     نست
    0.38
    塩素
    0.37
     συμπ
    0.37
     angin
    0.37
     Ref
    0.37
     Frey
    0.37
    POSITIVE LOGITS
    .*/
    0.46
    operations
    0.45
    former
    0.43
    behavior
    0.42
    Person
    0.42
    Operations
    0.41
    ult
    0.40
    antwoord
    0.40
    ineties
    0.40
    person
    0.40
    Activations Density 0.006%

    No Known Activations